Keyulu Xu, Mozhi Zhang, Jingling Li, Simon Shaolei Du, Ken-Ichi Kawarabayashi, Stefanie Jegelka
tl;dr: We study how neural networks trained by gradient descent extrapolate.
We study how neural networks trained by gradient descent extrapolate, i.e., what they learn outside the support of the training distribution. Previous works report mixed empirical results when extrapolating with neural networks: while feedforward neural networks, a.k.a. multilayer perceptrons (MLPs), do not extrapolate well in certain simple tasks, Graph Neural Networks (GNNs) -- structured networks with MLP modules -- have shown some success in more complex tasks. Working towards a theoretical explanation, we identify conditions under which MLPs and GNNs extrapolate well. First, we quantify the observation that ReLU MLPs quickly converge to linear functions along any direction from the origin, which implies that ReLU MLPs do not extrapolate most nonlinear functions. But, they can provably learn a linear target function when the training distribution is sufficiently diverse. Second, in connection to analyzing the successes and limitations of GNNs, these results suggest a hypothesis for which we provide theoretical and empirical evidence: the success of GNNs in extrapolating algorithmic tasks to new data (e.g., larger graphs or edge weights) relies on encoding task-specific non-linearities in the architecture or features. Our theoretical analysis builds on a connection of over-parameterized networks to the neural tangent kernel. Empirically, our theory holds across different training settings.
Bo Zhao, Konda Reddy Mopuri, Hakan Bilen
tl;dr: This paper proposes a training set synthesis technique that learns to produce a small set of informative samples for training deep neural networks from scratch in a small fraction of computational cost while achieving as close results as possible.
As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for data-efficient learning, called Dataset Condensation, that learns to condense large dataset into a small set of informative synthetic samples for training deep neural networks from scratch. We formulate this goal as a gradient matching problem between the gradients of deep neural network weights that are trained on the original and our synthetic data. We rigorously evaluate its performance in several computer vision benchmarks and demonstrate that it significantly outperforms the state-of-the-art methods. Finally we explore the use of our method in continual learning and neural architecture search and report promising gains when limited memory and computations are available.
David A. Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge, Dylan Paiton
tl;dr: Our work addresses key issues in disentanglement research for moving towards more natural settings.
Disentangling the underlying generative factors from complex data has so far been limited to carefully constructed scenarios. We propose a path towards natural data by first showing that the statistics of natural data provide enough structure to enable disentanglement, both theoretically and empirically. Specifically, we provide evidence that objects in natural movies undergo transitions that are typically small in magnitude with occasional large jumps, which is characteristic of a temporally sparse distribution. To address this finding we provide a novel proof that relies on a sparse prior on temporally adjacent observations to recover the true latent variables up to permutations and sign flips, directly providing a stronger result than previous work. We show that equipping practical estimation methods with our prior often surpasses the current state-of-the-art on several established benchmark datasets without any impractical assumptions, such as knowledge of the number of changing generative factors. Furthermore, we contribute two new benchmarks, Natural Sprites and KITTI Masks, which integrate the measured natural dynamics to enable disentanglement evaluation with more realistic datasets. We leverage these benchmarks to test our theory, demonstrating improved performance. We also identify non-obvious challenges for current methods in scaling to more natural domains. Taken together our work addresses key issues in disentanglement research for moving towards more natural settings.
Luca Weihs, Aniruddha Kembhavi, Kiana Ehsani, Sarah M Pratt, Winson Han, Alvaro Herrasti, Eric Kolve, Dustin Schwenk, Roozbeh Mottaghi, Ali Farhadi
tl;dr: We show the representation learned through interaction and gameplay generalizes better compared to passive and static representation learning methods.
A growing body of research suggests that embodied gameplay, prevalent not just in human cultures but across a variety of animal species including turtles and ravens, is critical in developing the neural flexibility for creative problem solving, decision making, and socialization. Comparatively little is known regarding the impact of embodied gameplay upon artificial agents. While recent work has produced agents proficient in abstract games, these environments are far removed the real world and thus these agents can provide little insight into the advantages of embodied play. Hiding games, such as hide-and-seek, played universally, provide a rich ground for studying the impact of embodied gameplay on representation learning in the context of perspective taking, secret keeping, and false belief understanding. Here we are the first to show that embodied adversarial reinforcement learning agents playing Cache, a variant of hide-and-seek, in a high fidelity, interactive, environment, learn generalizable representations of their observations encoding information such as object permanence, free space, and containment. Moving closer to biologically motivated learning strategies, our agents' representations, enhanced by intentionality and memory, are developed through interaction and play. These results serve as a model for studying how facets of vision develop through interaction, provide an experimental framework for assessing what is learned by artificial agents, and demonstrates the value of moving from large, static, datasets towards experiential, interactive, representation learning.
Erik Arakelyan, Daniel Daza, Pasquale Minervini, Michael Cochez
tl;dr: We show how to answer complex queries by answering their sub-queries via neural link predictors, aggregating results via t-norms and t-conorms, and identifying the optimal variable substitutions by solving an optimisation problem.
Neural link predictors are immensely useful for identifying missing edges in large scale Knowledge Graphs. However, it is still not clear how to use these models for answering more complex queries that arise in a number of domains, such as queries using logical conjunctions ($\land$), disjunctions ($\lor$) and existential quantifiers ($\exists$), while accounting for missing edges. In this work, we propose a framework for efficiently answering complex queries on incomplete Knowledge Graphs. We translate each query into an end-to-end differentiable objective, where the truth value of each atom is computed by a pre-trained neural link predictor. We then analyse two solutions to the optimisation problem, including gradient-based and combinatorial search. In our experiments, the proposed approach produces more accurate results than state-of-the-art methods --- black-box neural models trained on millions of generated queries --- without the need of training on a large and diverse set of complex queries. Using orders of magnitude less training data, we obtain relative improvements ranging from 8% up to 40% in Hits@3 across different knowledge graphs containing factual information. Finally, we demonstrate that it is possible to explain the outcome of our model in terms of the intermediate solutions identified for each of the complex query atoms. All our source code and datasets are available online, at
Brenden K Petersen, Mikel Landajuela Larma, Terrell N. Mundhenk, Claudio Prata Santiago, Soo Kyung Kim, Joanne Taery Kim
tl;dr: A deep learning approach to symbolic regression, in which an autoregressive RNN emits a distribution over expressions that is optimized using a risk-seeking policy gradient.
Discovering the underlying mathematical expressions describing a dataset is a core challenge for artificial intelligence. This is the problem of $\textit{symbolic regression}$. Despite recent advances in training neural networks to solve complex tasks, deep learning approaches to symbolic regression are underexplored. We propose a framework that leverages deep learning for symbolic regression via a simple idea: use a large model to search the space of small models. Specifically, we use a recurrent neural network to emit a distribution over tractable mathematical expressions and employ a novel risk-seeking policy gradient to train the network to generate better-fitting expressions. Our algorithm outperforms several baseline methods (including Eureqa, the gold standard for symbolic regression) in its ability to exactly recover symbolic expressions on a series of benchmark problems, both with and without added noise. More broadly, our contributions include a framework that can be applied to optimize hierarchical, variable-length objects under a black-box performance metric, with the ability to incorporate constraints in situ, and a risk-seeking policy gradient formulation that optimizes for best-case performance instead of expected performance.
Aston Zhang, Yi Tay, SHUAI Zhang, Alvin Chan, Anh Tuan Luu, Siu Hui, Jie Fu
tl;dr: We propose to parameterize hypercomplex multiplications using arbitrarily $1/n$ learnable parameters compared with the fully-connected layer counterpart.
Recent works have demonstrated reasonable success of representation learning in hypercomplex space. Specifically, “fully-connected layers with quaternions” (quaternions are 4D hypercomplex numbers), which replace real-valued matrix multiplications in fully-connected layers with Hamilton products of quaternions, both enjoy parameter savings with only 1/4 learnable parameters and achieve comparable performance in various applications. However, one key caveat is that hypercomplex space only exists at very few predefined dimensions (4D, 8D, and 16D). This restricts the flexibility of models that leverage hypercomplex multiplications. To this end, we propose parameterizing hypercomplex multiplications, allowing models to learn multiplication rules from data regardless of whether such rules are predefined. As a result, our method not only subsumes the Hamilton product, but also learns to operate on any arbitrary $n$D hypercomplex space, providing more architectural flexibility using arbitrarily $1/n$ learnable parameters compared with the fully-connected layer counterpart. Experiments of applications to the LSTM and transformer models on natural language inference, machine translation, text style transfer, and subject verb agreement demonstrate architectural flexibility and effectiveness of the proposed approach.
Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, Jifeng Dai
tl;dr: Deformable DETR is an efficient and fast-converging end-to-end object detector. It mitigates the high complexity and slow convergence issues of DETR via a novel sampling-based efficient attention mechanism.
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10$\times$ less training epochs. Extensive experiments on the COCO benchmark demonstrate the effectiveness of our approach. Code is released at
Marcin Andrychowicz, Anton Raichuk, Piotr Stańczyk, Manu Orsini, Sertan Girgin, Raphaël Marinier, Leonard Hussenot, Matthieu Geist, Olivier Pietquin, Marcin Michalski, Sylvain Gelly, Olivier Bachem
tl;dr: We conduct a large-scale empirical study that provides insights and practical recommendations for the training of on-policy deep actor-critic RL agents.
In recent years, reinforcement learning (RL) has been successfully applied to many different continuous control tasks. While RL algorithms are often conceptually simple, their state-of-the-art implementations take numerous low- and high-level design decisions that strongly affect the performance of the resulting agents. Those choices are usually not extensively discussed in the literature, leading to discrepancy between published descriptions of algorithms and their implementations. This makes it hard to attribute progress in RL and slows down overall progress [Engstrom'20]. As a step towards filling that gap, we implement >50 such ``"choices" in a unified on-policy deep actor-critic framework, allowing us to investigate their impact in a large-scale empirical study. We train over 250'000 agents in five continuous control environments of different complexity and provide insights and practical recommendations for the training of on-policy deep actor-critic RL agents.
Mike Gartrell, Insu Han, Elvis Dohmatob, Jennifer Gillenwater, Victor-Emmanuel Brunel
tl;dr: We propose scalable learning and maximum a posteriori (MAP) inference algorithms for nonsymmetric determinantal point processes (DPPs).
Determinantal point processes (DPPs) have attracted significant attention in machine learning for their ability to model subsets drawn from a large item collection. Recent work shows that nonsymmetric DPP (NDPP) kernels have significant advantages over symmetric kernels in terms of modeling power and predictive performance. However, for an item collection of size $M$, existing NDPP learning and inference algorithms require memory quadratic in $M$ and runtime cubic (for learning) or quadratic (for inference) in $M$, making them impractical for many typical subset selection tasks. In this work, we develop a learning algorithm with space and time requirements linear in $M$ by introducing a new NDPP kernel decomposition. We also derive a linear-complexity NDPP maximum a posteriori (MAP) inference algorithm that applies not only to our new kernel but also to that of prior work. Through evaluation on real-world datasets, we show that our algorithms scale significantly better, and can match the predictive performance of prior work.
Ainesh Bakshi, Chiranjib Bhattacharyya, Ravi Kannan, David Woodruff, Samson Zhou
tl;dr: We obtain the first input sparsity runtime algorithm for the problem of learning a latent simplex.
We consider the problem of learning a latent $k$-vertex simplex $K\in\mathbb{R}^d$, given $\mathbf{A}\in\mathbb{R}^{d\times n}$, which can be viewed as $n$ data points that are formed by randomly perturbing some latent points in $K$, possibly beyond $K$. A large class of latent variable models, such as adversarial clustering, mixed membership stochastic block models, and topic models can be cast in this view of learning a latent simplex. Bhattacharyya and Kannan (SODA 2020) give an algorithm for learning such a $k$-vertex latent simplex in time roughly $O(k\cdot\text{nnz}(\mathbf{A}))$, where $\text{nnz}(\mathbf{A})$ is the number of non-zeros in $\mathbf{A}$. We show that the dependence on $k$ in the running time is unnecessary given a natural assumption about the mass of the top $k$ singular values of $\mathbf{A}$, which holds in many of these applications. Further, we show this assumption is necessary, as otherwise an algorithm for learning a latent simplex would imply a better low rank approximation algorithm than what is known. We obtain a spectral low-rank approximation to $\mathbf{A}$ in input-sparsity time and show that the column space thus obtained has small $\sin\Theta$ (angular) distance to the right top-$k$ singular space of $\mathbf{A}$. Our algorithm then selects $k$ points in the low-rank subspace with the largest inner product (in absolute value) with $k$ carefully chosen random vectors. By working in the low-rank subspace, we avoid reading the entire matrix in each iteration and thus circumvent the $\Theta(k\cdot\text{nnz}(\mathbf{A}))$ running time.
Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma
tl;dr: This paper provides accuracy guarantees for self-training with deep networks on polynomial unlabeled samples for semi-supervised learning, unsupervised domain adaptation, and unsupervised learning.
Self-training algorithms, which train a model to fit pseudolabels predicted by another previously-learned model, have been very successful for learning with unlabeled data using neural networks. However, the current theoretical understanding of self-training only applies to linear models. This work provides a unified theoretical analysis of self-training with deep networks for semi-supervised learning, unsupervised domain adaptation, and unsupervised learning. At the core of our analysis is a simple but realistic “expansion” assumption, which states that a low-probability subset of the data must expand to a neighborhood with large probability relative to the subset. We also assume that neighborhoods of examples in different classes have minimal overlap. We prove that under these assumptions, the minimizers of population objectives based on self-training and input-consistency regularization will achieve high accuracy with respect to ground-truth labels. By using off-the-shelf generalization bounds, we immediately convert this result to sample complexity guarantees for neural nets that are polynomial in the margin and Lipschitzness. Our results help explain the empirical successes of recently proposed self-training algorithms which use input consistency regularization.
Yuan Yin, Vincent LE GUEN, Jérémie DONA, Emmanuel de Bezenac, Ibrahim Ayed, Nicolas THOME, patrick gallinari
tl;dr: We propose a new principled framework for combining physical models with deep data-driven networks, for which we provide theoretical decomposition guarantees.
Forecasting complex dynamical phenomena in settings where only partial knowledge of their dynamics is available is a prevalent problem across various scientific fields. While purely data-driven approaches are arguably insufficient in this context, standard physical modeling based approaches tend to be over-simplistic, inducing non-negligible errors. In this work, we introduce the APHYNITY framework, a principled approach for augmenting incomplete physical dynamics described by differential equations with deep data-driven models. It consists in decomposing the dynamics into two components: a physical component accounting for the dynamics for which we have some prior knowledge, and a data-driven component accounting for errors of the physical model. The learning problem is carefully formulated such that the physical model explains as much of the data as possible, while the data-driven component only describes information that cannot be captured by the physical model, no more, no less. This not only provides the existence and uniqueness for this decomposition, but also ensures interpretability and benefits generalization. Experiments made on three important use cases, each representative of a different family of phenomena, i.e. reaction-diffusion equations, wave equations and the non-linear damped pendulum, show that APHYNITY can efficiently leverage approximate physical models to accurately forecast the evolution of the system and correctly identify relevant physical parameters.
Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
tl;dr: A general framework for training and sampling from score-based models that unifies and generalizes previous methods, allows likelihood computation, and enables controllable generation.
Creating noise from data is easy; creating data from noise is generative modeling. We present a stochastic differential equation (SDE) that smoothly transforms a complex data distribution to a known prior distribution by slowly injecting noise, and a corresponding reverse-time SDE that transforms the prior distribution back into the data distribution by slowly removing the noise. Crucially, the reverse-time SDE depends only on the time-dependent gradient field (a.k.a., score) of the perturbed data distribution. By leveraging advances in score-based generative modeling, we can accurately estimate these scores with neural networks, and use numerical SDE solvers to generate samples. We show that this framework encapsulates previous approaches in score-based generative modeling and diffusion probabilistic modeling, allowing for new sampling procedures and new modeling capabilities. In particular, we introduce a predictor-corrector framework to correct errors in the evolution of the discretized reverse-time SDE. We also derive an equivalent neural ODE that samples from the same distribution as the SDE, but additionally enables exact likelihood computation, and improved sampling efficiency. In addition, we provide a new way to solve inverse problems with score-based models, as demonstrated with experiments on class-conditional generation, image inpainting, and colorization. Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9.89 and FID of 2.20, a competitive likelihood of 2.99 bits/dim, and demonstrate high fidelity generation of $1024\times 1024$ images for the first time from a score-based generative model.
Matthew Smart, Anton Zilman
tl;dr: Hopfield networks with correlated patterns can be mapped to Restricted Boltzmann Machines with orthogonal weights.
Hopfield networks (HNs) and Restricted Boltzmann Machines (RBMs) are two important models at the interface of statistical physics, machine learning, and neuroscience. Recently, there has been interest in the relationship between HNs and RBMs, due to their similarity under the statistical mechanics formalism. An exact mapping between HNs and RBMs has been previously noted for the special case of orthogonal (“uncorrelated”) encoded patterns. We present here an exact mapping in the case of correlated pattern HNs, which are more broadly applicable to existing datasets. Specifically, we show that any HN with $N$ binary variables and $p<N$ potentially correlated binary patterns can be transformed into an RBM with $N$ binary visible variables and $p$ gaussian hidden variables. We outline the conditions under which the reverse mapping exists, and conduct experiments on the MNIST dataset which suggest the mapping provides a useful initialization to the RBM weights. We discuss extensions, the potential importance of this correspondence for the training of RBMs, and for understanding the performance of feature extraction methods which utilize RBMs.
Waiss Azizian, marc lelarge
Various classes of Graph Neural Networks (GNN) have been proposed and shown to be successful in a wide range of applications with graph structured data. In this paper, we propose a theoretical framework able to compare the expressive power of these GNN architectures. The current universality theorems only apply to intractable classes of GNNs. Here, we prove the first approximation guarantees for practical GNNs, paving the way for a better understanding of their generalization. Our theoretical results are proved for invariant GNNs computing a graph embedding (permutation of the nodes of the input graph does not affect the output) and equivariant GNNs computing an embedding of the nodes (permutation of the input permutes the output). We show that Folklore Graph Neural Networks (FGNN), which are tensor based GNNs augmented with matrix multiplication are the most expressive architectures proposed so far for a given tensor order. We illustrate our results on the Quadratic Assignment Problem (a NP-Hard combinatorial problem) by showing that FGNNs are able to learn how to solve the problem, leading to much better average performances than existing algorithms (based on spectral, SDP or other GNNs architectures). On a practical side, we also implement masked tensors to handle batches of graphs of varying sizes.
Ruochen Wang, Minhao Cheng, Xiangning Chen, Xiaocheng Tang, Cho-Jui Hsieh
Differentiable Neural Architecture Search is one of the most popular Neural Architecture Search (NAS) methods for its search efficiency and simplicity, accomplished by jointly optimizing the model weight and architecture parameters in a weight-sharing supernet via gradient-based algorithms. At the end of the search phase, the operations with the largest architecture parameters will be selected to form the final architecture, with the implicit assumption that the values of architecture parameters reflect the operation strength. While much has been discussed about the supernet's optimization, the architecture selection process has received little attention. We provide empirical and theoretical analysis to show that the magnitude of architecture parameters does not necessarily indicate how much the operation contributes to the supernet's performance. We propose an alternative perturbation-based architecture selection that directly measures each operation's influence on the supernet. We re-evaluate several differentiable NAS methods with the proposed architecture selection and find that it is able to extract significantly improved architectures from the underlying supernets consistently. Furthermore, we find that several failure modes of DARTS can be greatly alleviated with the proposed selection method, indicating that much of the poor generalization observed in DARTS can be attributed to the failure of magnitude-based architecture selection rather than entirely the optimization of its supernet.
Biao Zhang, Ankur Bapna, Rico Sennrich, Orhan Firat
tl;dr: We investigate and improve parameter-sharing strategies in multilingual Transformers by utilizing conditional computation.
Using a mix of shared and language-specific (LS) parameters has shown promise in multilingual neural machine translation (MNMT), but the question of when and where LS capacity matters most is still under-studied. We offer such a study by proposing conditional language-specific routing (CLSR). CLSR employs hard binary gates conditioned on token representations to dynamically select LS or shared paths. By manipulating these gates, it can schedule LS capacity across sub-layers in MNMT subject to the guidance of translation signals and budget constraints. Moreover, CLSR can easily scale up to massively multilingual settings. Experiments with Transformer on OPUS-100 and WMT datasets show that: 1) MNMT is sensitive to both the amount and the position of LS modeling: distributing 10%-30% LS computation to the top and/or bottom encoder/decoder layers delivers the best performance; and 2) one-to-many translation benefits more from CLSR compared to many-to-one translation, particularly with unbalanced training data. Our study further verifies the trade-off between the shared capacity and LS capacity for multilingual translation. We corroborate our analysis by confirming the soundness of our findings as foundation of our improved multilingual Transformers. Source code and models are available at
Nicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio Petroni
tl;dr: We address entity retrieval by generating their unique name identifiers, left to right, in an autoregressive fashion, and conditioned on the context showing SOTA results in more than 20 datasets with a tiny fraction of the memory of recent systems.
Entities are at the center of how we represent and aggregate knowledge. For instance, Encyclopedias such as Wikipedia are structured by entities (e.g., one per Wikipedia article). The ability to retrieve such entities given a query is fundamental for knowledge-intensive tasks such as entity linking and open-domain question answering. One way to understand current approaches is as classifiers among atomic labels, one for each entity. Their weight vectors are dense entity representations produced by encoding entity meta information such as their descriptions. This approach leads to several shortcomings: (i) context and entity affinity is mainly captured through a vector dot product, potentially missing fine-grained interactions between the two; (ii) a large memory footprint is needed to store dense representations when considering large entity sets; (iii) an appropriately hard set of negative data has to be subsampled at training time. In this work, we propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion and conditioned on the context. This enables us to mitigate the aforementioned technical issues since: (i) the autoregressive formulation allows us to directly capture relations between context and entity name, effectively cross encoding both; (ii) the memory footprint is greatly reduced because the parameters of our encoder-decoder architecture scale with vocabulary size, not entity count; (iii) the exact softmax loss can be efficiently computed without the need to subsample negative data. We show the efficacy of the approach, experimenting with more than 20 datasets on entity disambiguation, end-to-end entity linking and document retrieval tasks, achieving new state-of-the-art or very competitive results while using a tiny fraction of the memory footprint of competing systems. Finally, we demonstrate that new entities can be added by simply specifying their unambiguous name. Code and pre-trained models at
Qiang Zhang, Tete Xiao, Alexei A Efros, Lerrel Pinto, Xiaolong Wang
tl;dr: We learn correspondence across domains with different modalities, physics parameters, and morphologies for control tasks (in both simulation and real robot) with Dynamics Cycle-Consistency.
At the heart of many robotics problems is the challenge of learning correspondences across domains. For instance, imitation learning requires obtaining correspondence between humans and robots; sim-to-real requires correspondence between physics simulators and real hardware; transfer learning requires correspondences between different robot environments. In this paper, we propose to learn correspondence across such domains emphasizing on differing modalities (vision and internal state), physics parameters (mass and friction), and morphologies (number of limbs). Importantly, correspondences are learned using unpaired and randomly collected data from the two domains. We propose dynamics cycles that align dynamic robotic behavior across two domains using a cycle consistency constraint. Once this correspondence is found, we can directly transfer the policy trained on one domain to the other, without needing any additional fine-tuning on the second domain. We perform experiments across a variety of problem domains, both in simulation and on real robots. Our framework is able to align uncalibrated monocular video of a real robot arm to dynamic state-action trajectories of a simulated arm without paired data. Video demonstrations of our results are available at: .
Tobias Pfaff, Meire Fortunato, Alvaro Sanchez-Gonzalez, Peter Battaglia
tl;dr: We introduce a general method for learning the dynamics of complex physics systems accurately and efficiently on meshes
Mesh-based simulations are central to modeling complex physical systems in many disciplines across science and engineering. Mesh representations support powerful numerical integration methods and their resolution can be adapted to strike favorable trade-offs between accuracy and efficiency. However, high-dimensional scientific simulations are very expensive to run, and solvers and parameters must often be tuned individually to each system studied. Here we introduce MeshGraphNets, a framework for learning mesh-based simulations using graph neural networks. Our model can be trained to pass messages on a mesh graph and to adapt the mesh discretization during forward simulation. Our results show it can accurately predict the dynamics of a wide range of physical systems, including aerodynamics, structural mechanics, and cloth. The model's adaptivity supports learning resolution-independent dynamics and can scale to more complex state spaces at test time. Our method is also highly efficient, running 1-2 orders of magnitude faster than the simulation on which it is trained. Our approach broadens the range of problems on which neural network simulators can operate and promises to improve the efficiency of complex, scientific modeling tasks.
Amy Zhang, Rowan Thomas McAllister, Roberto Calandra, Yarin Gal, Sergey Levine
We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations that provide for effective downstream control and invariance to task-irrelevant details. Bisimulation metrics quantify behavioral similarity between states in continuous MDPs, which we propose using to learn robust latent representations which encode only the task-relevant information from observations. Our method trains encoders such that distances in latent space equal bisimulation distances in state space. We demonstrate the effectiveness of our method at disregarding task-irrelevant information using modified visual MuJoCo tasks, where the background is replaced with moving distractors and natural videos, while achieving SOTA performance. We also test a first-person highway driving task where our method learns invariance to clouds, weather, and time of day. Finally, we provide generalization results drawn from properties of bisimulation metrics, and links to causal inference.
Khai Nguyen, Nhat Ho, Tung Pham, Hung Bui
tl;dr: A new optimal transport distance based on slicing approach and its applications to generative modeling.
Sliced-Wasserstein distance (SW) and its variant, Max Sliced-Wasserstein distance (Max-SW), have been used widely in the recent years due to their fast computation and scalability even when the probability measures lie in a very high dimensional space. However, SW requires many unnecessary projection samples to approximate its value while Max-SW only uses the most important projection, which ignores the information of other useful directions. In order to account for these weaknesses, we propose a novel distance, named Distributional Sliced-Wasserstein distance (DSW), that finds an optimal distribution over projections that can balance between exploring distinctive projecting directions and the informativeness of projections themselves. We show that the DSW is a generalization of Max-SW, and it can be computed efficiently by searching for the optimal push-forward measure over a set of probability measures over the unit sphere satisfying certain regularizing constraints that favor distinct directions. Finally, we conduct extensive experiments with large-scale datasets to demonstrate the favorable performances of the proposed distances over the previous sliced-based distances in generative modeling applications.
Jingfeng Zhang, Jianing Zhu, Gang Niu, Bo Han, Masashi Sugiyama, Mohan Kankanhalli
tl;dr: This paper has proposed a novel adversarial training method, i.e., geometry-aware instance-reweighted adversarial training (GAIRAT), which sheds new lights on improving the adversarial training.
In adversarial machine learning, there was a common belief that robustness and accuracy hurt each other. The belief was challenged by recent studies where we can maintain the robustness and improve the accuracy. However, the other direction, whether we can keep the accuracy and improve the robustness, is conceptually and practically more interesting, since robust accuracy should be lower than standard accuracy for any model. In this paper, we show this direction is also promising. Firstly, we find even over-parameterized deep networks may still have insufficient model capacity, because adversarial training has an overwhelming smoothing effect. Secondly, given limited model capacity, we argue adversarial data should have unequal importance: geometrically speaking, a natural data point closer to/farther from the class boundary is less/more robust, and the corresponding adversarial data point should be assigned with larger/smaller weight. Finally, to implement the idea, we propose geometry-aware instance-reweighted adversarial training, where the weights are based on how difficult it is to attack a natural data point. Experiments show that our proposal boosts the robustness of standard adversarial training; combining two directions, we improve both robustness and accuracy of standard adversarial training.
Xiaoxia Wu, Ethan Dyer, Behnam Neyshabur
tl;dr: We conduct extensive experiments over thousands of orderings to investigate the effectiveness of three kinds of learning: curriculum, anti-curriculum, and random-curriculum.
Inspired by human learning, researchers have proposed ordering examples during training based on their difficulty. Both curriculum learning, exposing a network to easier examples early in training, and anti-curriculum learning, showing the most difficult examples first, have been suggested as improvements to the standard i.i.d. training. In this work, we set out to investigate the relative benefits of ordered learning. We first investigate the implicit curricula resulting from architectural and optimization bias and find that samples are learned in a highly consistent order. Next, to quantify the benefit of explicit curricula, we conduct extensive experiments over thousands of orderings spanning three kinds of learning: curriculum, anti-curriculum, and random-curriculum -- in which the size of the training dataset is dynamically increased over time, but the examples are randomly ordered. We find that for standard benchmark datasets, curricula have only marginal benefits, and that randomly ordered samples perform as well or better than curricula and anti-curricula, suggesting that any benefit is entirely due to the dynamic training set size. Inspired by common use cases of curriculum learning in practice, we investigate the role of limited training time budget and noisy data in the success of curriculum learning. Our experiments demonstrate that curriculum, but not anti-curriculum or random ordering can indeed improve the performance either with limited training time budget or in the existence of noisy data.
Yoshua Bengio, Prateek Gupta, Tegan Maharaj, Nasim Rahaman, Martin Weiss, Tristan Deleu, Eilif Benjamin Muller, Meng Qu, victor schmidt, Pierre-luc St-charles, hannah alsdurf, Olexa Bilaniuk, david buckeridge, gaetan caron, pierre luc carrier, Joumana Ghosn, satya ortiz gagne, Christopher Pal, Irina Rish, Bernhard Schölkopf, abhinav sharma, Jian Tang, andrew williams
tl;dr: Proposes a framework called Proactive Contact Tracing which uses distributed inference of expected Covid-19 infectiousness to provide individualized, private recommendations.
The COVID-19 pandemic has spread rapidly worldwide, overwhelming manual contact tracing in many countries and resulting in widespread lockdowns for emergency containment. Large-scale digital contact tracing (DCT) has emerged as a potential solution to resume economic and social activity while minimizing spread of the virus. Various DCT methods have been proposed, each making trade-offs be-tween privacy, mobility restrictions, and public health. The most common approach, binary contact tracing (BCT), models infection as a binary event, informed only by an individual’s test results, with corresponding binary recommendations that either all or none of the individual’s contacts quarantine. BCT ignores the inherent uncertainty in contacts and the infection process, which could be used to tailor messaging to high-risk individuals, and prompt proactive testing or earlier warnings. It also does not make use of observations such as symptoms or pre-existing medical conditions, which could be used to make more accurate infectiousness predictions. In this paper, we use a recently-proposed COVID-19 epidemiological simulator to develop and test methods that can be deployed to a smartphone to locally and proactively predict an individual’s infectiousness (risk of infecting others) based on their contact history and other information, while respecting strong privacy constraints. Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual’s contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT). Similarly to other works, we find that compared to no tracing, all DCT methods tested are able to reduce spread of the disease and thus save lives, even at low adoption rates, strongly supporting a role for DCT methods in managing the pandemic. Further, we find a deep-learning based PCT method which improves over BCT for equivalent average mobility, suggesting PCT could help in safe re-opening and second-wave prevention.
Ian Gemp, Brian McWilliams, Claire Vernade, Thore Graepel
tl;dr: We formulate the solution to PCA as the Nash of a suitable game with accompanying algorithm that we demonstrate on a 200TB dataset.
We present a novel view on principal components analysis as a competitive game in which each approximate eigenvector is controlled by a player whose goal is to maximize their own utility function. We analyze the properties of this PCA game and the behavior of its gradient based updates. The resulting algorithm---which combines elements from Oja's rule with a generalized Gram-Schmidt orthogonalization---is naturally decentralized and hence parallelizable through message passing. We demonstrate the scalability of the algorithm with experiments on large image datasets and neural network activations. We discuss how this new view of PCA as a differentiable game can lead to further algorithmic developments and insights.
Xingang Pan, Bo Dai, Ziwei Liu, Chen Change Loy, Ping Luo
tl;dr: Unsupervised 3D Shape Reconstruction from 2D Image GANs
Natural images are projections of 3D objects on a 2D image plane. While state-of-the-art 2D generative models like GANs show unprecedented quality in modeling the natural image manifold, it is unclear whether they implicitly capture the underlying 3D object structures. And if so, how could we exploit such knowledge to recover the 3D shapes of objects in the images? To answer these questions, in this work, we present the first attempt to directly mine 3D geometric cues from an off-the-shelf 2D GAN that is trained on RGB images only. Through our investigation, we found that such a pre-trained GAN indeed contains rich 3D knowledge and thus can be used to recover 3D shape from a single 2D image in an unsupervised manner. The core of our framework is an iterative strategy that explores and exploits diverse viewpoint and lighting variations in the GAN image manifold. The framework does not require 2D keypoint or 3D annotations, or strong assumptions on object shapes (e.g. shapes are symmetric), yet it successfully recovers 3D shapes with high precision for human faces, cats, cars, and buildings. The recovered 3D shapes immediately allow high-quality image editing like relighting and object rotation. We quantitatively demonstrate the effectiveness of our approach compared to previous methods in both 3D shape reconstruction and face rotation. Our code is available at
Harsh Mehta, Ashok Cutkosky, Behnam Neyshabur
tl;dr: Through studying the effect of scale of initialization on generalization, we come up with an alignment measure that correlations with generalization of deep models.
We construct an experimental setup in which changing the scale of initialization strongly impacts the implicit regularization induced by SGD, interpolating from good generalization performance to completely memorizing the training set while making little progress on the test set. Moreover, we find that the extent and manner in which generalization ability is affected depends on the activation and loss function used, with sin activation being the most extreme. In the case of the homogeneous ReLU activation, we show that this behavior can be attributed to the loss function. Our empirical investigation reveals that increasing the scale of initialization correlates with misalignment of representations and gradients across examples in the same class. This insight allows us to device an alignment measure over gradients and representations which can capture this phenomenon. We demonstrate that our alignment measure correlates with generalization of deep models trained on image classification tasks.
Alexander Richard, Dejan Markovic, Israel D. Gebru, Steven Krenn, Gladstone Alexander Butler, Fernando Torre, Yaser Sheikh
tl;dr: We propose an end-to-end approach to neural binaural sound synthesis that for the first time outperforms DSP-based methods in a qualitative evaluation and in a perceptual study.
We present a neural rendering approach for binaural sound synthesis that can produce realistic and spatially accurate binaural sound in realtime. The network takes, as input, a single-channel audio source and synthesizes, as output, two-channel binaural sound, conditioned on the relative position and orientation of the listener with respect to the source. We investigate deficiencies of the l2-loss on raw waveforms in a theoretical analysis and introduce an improved loss that overcomes these limitations. In an empirical evaluation, we establish that our approach is the first to generate spatially accurate waveform outputs (as measured by real recordings) and outperforms existing approaches by a considerable margin, both quantitatively and in a perceptual study. Dataset and code are available online.
Atsushi Nitanda, Taiji Suzuki
tl;dr: This is the first paper to overcome technical challenges of achieving the optimal convergence rate under the NTK regime.
We analyze the convergence of the averaged stochastic gradient descent for overparameterized two-layer neural networks for regression problems. It was recently found that a neural tangent kernel (NTK) plays an important role in showing the global convergence of gradient-based methods under the NTK regime, where the learning dynamics for overparameterized neural networks can be almost characterized by that for the associated reproducing kernel Hilbert space (RKHS). However, there is still room for a convergence rate analysis in the NTK regime. In this study, we show that the averaged stochastic gradient descent can achieve the minimax optimal convergence rate, with the global convergence guarantee, by exploiting the complexities of the target function and the RKHS associated with the NTK. Moreover, we show that the target function specified by the NTK of a ReLU network can be learned at the optimal convergence rate through a smooth approximation of a ReLU network under certain conditions.
Zhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, Bryan Catanzaro
tl;dr: DiffWave is a versatile diffusion probabilistic model for waveform generation, which matches the state-of-the-art neural vocoder in terms of quality and can generate abundant realistic voices in time-domain without any conditional information.
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts the white noise signal into structured waveform through a Markov chain with a constant number of steps at synthesis. It is efficiently trained by optimizing a variant of variational bound on the data likelihood. DiffWave produces high-fidelity audios in different waveform generation tasks, including neural vocoding conditioned on mel spectrogram, class-conditional generation, and unconditional generation. We demonstrate that DiffWave matches a strong WaveNet vocoder in terms of speech quality (MOS: 4.44 versus 4.43), while synthesizing orders of magnitude faster. In particular, it significantly outperforms autoregressive and GAN-based waveform models in the challenging unconditional generation task in terms of audio quality and sample diversity from various automatic and human evaluations.
Talya Eden, Piotr Indyk, Shyam Narayanan, Ronitt Rubinfeld, Sandeep Silwal, Tal Wagner
tl;dr: A learning-based algorithm for support size estimation, which given a sufficiently accurate predictor, improves both provably and empirically over state-of-the-art algorithms that do not use a predictor.
We consider the problem of estimating the number of distinct elements in a large data set (or, equivalently, the support size of the distribution induced by the data set) from a random sample of its elements. The problem occurs in many applications, including biology, genomics, computer systems and linguistics. A line of research spanning the last decade resulted in algorithms that estimate the support up to $ \pm \varepsilon n$ from a sample of size $O(\log^2(1/\varepsilon) \cdot n/\log n)$, where $n$ is the data set size. Unfortunately, this bound is known to be tight, limiting further improvements to the complexity of this problem. In this paper we consider estimation algorithms augmented with a machine-learning-based predictor that, given any element, returns an estimation of its frequency. We show that if the predictor is correct up to a constant approximation factor, then the sample complexity can be reduced significantly, to $$ \ \log (1/\varepsilon) \cdot n^{1-\Theta(1/\log(1/\varepsilon))}. $$ We evaluate the proposed algorithms on a collection of data sets, using the neural-network based estimators from {Hsu et al, ICLR'19} as predictors. Our experiments demonstrate substantial (up to 3x) improvements in the estimation accuracy compared to the state of the art algorithm.
Elliot Meyerson, Risto Miikkulainen
tl;dr: Learn a single model across "unrelated" tasks by embedding their input and output variables in a shared space.
This paper frames a general prediction system as an observer traveling around a continuous space, measuring values at some locations, and predicting them at others. The observer is completely agnostic about any particular task being solved; it cares only about measurement locations and their values. This perspective leads to a machine learning framework in which seemingly unrelated tasks can be solved by a single model, by embedding their input and output variables into a shared space. An implementation of the framework is developed in which these variable embeddings are learned jointly with internal model parameters. In experiments, the approach is shown to (1) recover intuitive locations of variables in space and time, (2) exploit regularities across related datasets with completely disjoint input and output spaces, and (3) exploit regularities across seemingly unrelated tasks, outperforming task-specific single-task models and multi-task learning alternatives. The results suggest that even seemingly unrelated tasks may originate from similar underlying processes, a fact that the traveling observer model can use to make better predictions.
Pim De Haan, Maurice Weiler, Taco Cohen, Max Welling
tl;dr: Expressive anisotropic mesh convolution without having to pick arbitrary kernel orientation by using gauge equivariance
A common approach to define convolutions on meshes is to interpret them as a graph and apply graph convolutional networks (GCNs). Such GCNs utilize isotropic kernels and are therefore insensitive to the relative orientation of vertices and thus to the geometry of the mesh as a whole. We propose Gauge Equivariant Mesh CNNs which generalize GCNs to apply anisotropic gauge equivariant kernels. Since the resulting features carry orientation information, we introduce a geometric message passing scheme defined by parallel transporting features over mesh edges. Our experiments validate the significantly improved expressivity of the proposed model over conventional GCNs and other methods.
Deunsol Yoon, Sunghoon Hong, Byung-Jun Lee, Kee-Eung Kim
tl;dr: We present an off-policy actor-critic approach that effectively tackles the unique challenges in power grid management by reinforcement learning, adopting the hierarchical policy together with the afterstate representation.
Safe and reliable electricity transmission in power grids is crucial for modern society. It is thus quite natural that there has been a growing interest in the automatic management of power grids, exemplified by the Learning to Run a Power Network Challenge (L2RPN), modeling the problem as a reinforcement learning (RL) task. However, it is highly challenging to manage a real-world scale power grid, mostly due to the massive scale of its state and action space. In this paper, we present an off-policy actor-critic approach that effectively tackles the unique challenges in power grid management by RL, adopting the hierarchical policy together with the afterstate representation. Our agent ranked first in the latest challenge (L2RPN WCCI 2020), being able to avoid disastrous situations while maintaining the highest level of operational efficiency in every test scenarios. This paper provides a formal description of the algorithmic aspect of our approach, as well as further experimental studies on diverse power grids.
Deniz Oktay, Nick McGreivy, Joshua Aduol, Alex Beatson, Ryan P Adams
tl;dr: We develop a general framework and approach for randomized automatic differentiation (RAD), which can allow unbiased gradient estimates to be computed with reduced memory in return for variance.
The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives. The AD techniques underlying these tools were designed to compute exact gradients to numerical precision, but modern machine learning models are almost always trained with stochastic gradient descent. Why spend computation and memory on exact (minibatch) gradients only to use them for stochastic optimization? We develop a general framework and approach for randomized automatic differentiation (RAD), which can allow unbiased gradient estimates to be computed with reduced memory in return for variance. We examine limitations of the general approach, and argue that we must leverage problem specific structure to realize benefits. We develop RAD techniques for a variety of simple neural network architectures, and show that for a fixed memory budget, RAD converges in fewer iterations than using a small batch size for feedforward networks, and in a similar number for recurrent networks. We also show that RAD can be applied to scientific computing, and use it to develop a low-memory stochastic gradient method for optimizing the control parameters of a linear reaction-diffusion PDE representing a fission reactor.
Sanjeevan Ahilan, Peter Dayan
tl;dr: We improve multi-agent learning by relabelling past experience to better reflect current communication policies
We consider the problem of learning to communicate using multi-agent reinforcement learning (MARL). A common approach is to learn off-policy, using data sampled from a replay buffer. However, messages received in the past may not accurately reflect the current communication policy of each agent, and this complicates learning. We therefore introduce a 'communication correction' which accounts for the non-stationarity of observed communication induced by multi-agent learning. It works by relabelling the received message to make it likely under the communicator's current policy, and thus be a better reflection of the receiver's current environment. To account for cases in which agents are both senders and receivers, we introduce an ordered relabelling scheme. Our correction is computationally efficient and can be integrated with a range of off-policy algorithms. We find in our experiments that it substantially improves the ability of communicating MARL systems to learn across a variety of cooperative and competitive tasks.
Rewon Child
tl;dr: We argue deeper VAEs should perform better, implement one, and show it outperforms all PixelCNN-based autoregressive models in likelihood, while being substantially more efficient.
We present a hierarchical VAE that, for the first time, generates samples quickly $\textit{and}$ outperforms the PixelCNN in log-likelihood on all natural image benchmarks. We begin by observing that, in theory, VAEs can actually represent autoregressive models, as well as faster, better models if they exist, when made sufficiently deep. Despite this, autoregressive models have historically outperformed VAEs in log-likelihood. We test if insufficient depth explains why by scaling a VAE to greater stochastic depth than previously explored and evaluating it CIFAR-10, ImageNet, and FFHQ. In comparison to the PixelCNN, these very deep VAEs achieve higher likelihoods, use fewer parameters, generate samples thousands of times faster, and are more easily applied to high-resolution images. Qualitative studies suggest this is because the VAE learns efficient hierarchical visual representations. We release our source code and models at
Yikai Zhang, Songzhu Zheng, Pengxiang Wu, Mayank Goswami, Chao Chen
tl;dr: We propose a progressive label correction approach for noisy label learning task.
Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing approaches to handling noisy labels fall into two categories: they either assume an ideal feature-independent noise, or remain heuristic without theoretical guarantees. In this paper, we propose to target a new family of feature-dependent label noise, which is much more general than commonly used i.i.d. label noise and encompasses a broad spectrum of noise patterns. Focusing on this general noise family, we propose a progressive label correction algorithm that iteratively corrects labels and refines the model. We provide theoretical guarantees showing that for a wide variety of (unknown) noise patterns, a classifier trained with this strategy converges to be consistent with the Bayes classifier. In experiments, our method outperforms SOTA baselines and is robust to various noise types and levels.
Ruosong Wang, Dean Foster, Sham M. Kakade
tl;dr: Exponential lower bounds for batch RL with linear function approximation.
Offline reinforcement learning seeks to utilize offline (observational) data to guide the learning of (causal) sequential decision making strategies. The hope is that offline reinforcement learning coupled with function approximation methods (to deal with the curse of dimensionality) can provide a means to help alleviate the excessive sample complexity burden in modern sequential decision making problems. However, the extent to which this broader approach can be effective is not well understood, where the literature largely consists of sufficient conditions. This work focuses on the basic question of what are necessary representational and distributional conditions that permit provable sample-efficient offline reinforcement learning. Perhaps surprisingly, our main result shows that even if: i) we have realizability in that the true value function of \emph{every} policy is linear in a given set of features and 2) our off-policy data has good coverage over all features (under a strong spectral condition), any algorithm still (information-theoretically) requires a number of offline samples that is exponential in the problem horizon to non-trivially estimate the value of \emph{any} given policy. Our results highlight that sample-efficient offline policy evaluation is not possible unless significantly stronger conditions hold; such conditions include either having low distribution shift (where the offline data distribution is close to the distribution of the policy to be evaluated) or significantly stronger representational conditions (beyond realizability).
Gobinda Saha, Isha Garg, Kaushik Roy
tl;dr: To avoid catastrophic forgetting in continual learning, we propose a novel approach where a neural network learns new tasks by taking gradient steps in the orthogonal direction to the gradient subspaces deemed important for past tasks.
The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial neural networks usually rely on network growth, importance based weight update or replay of old data from the memory. In contrast, we propose a novel approach where a neural network learns new tasks by taking gradient steps in the orthogonal direction to the gradient subspaces deemed important for the past tasks. We find the bases of these subspaces by analyzing network representations (activations) after learning each task with Singular Value Decomposition (SVD) in a single shot manner and store them in the memory as Gradient Projection Memory (GPM). With qualitative and quantitative analyses, we show that such orthogonal gradient descent induces minimum to no interference with the past tasks, thereby mitigates forgetting. We evaluate our algorithm on diverse image classification datasets with short and long sequences of tasks and report better or on-par performance compared to the state-of-the-art approaches.
Suraj Srinivas, Francois Fleuret
tl;dr: Input-gradients in discriminative neural net models capture information regarding an implicit density model, rather than that of the underlying discriminative model which it is intended to explain.
Current methods for the interpretability of discriminative deep neural networks commonly rely on the model's input-gradients, i.e., the gradients of the output logits w.r.t. the inputs. The common assumption is that these input-gradients contain information regarding $p_{\theta} ( y\mid \mathbf{x} )$, the model's discriminative capabilities, thus justifying their use for interpretability. However, in this work, we show that these input-gradients can be arbitrarily manipulated as a consequence of the shift-invariance of softmax without changing the discriminative function. This leaves an open question: given that input-gradients can be arbitrary, why are they highly structured and explanatory in standard models? In this work, we re-interpret the logits of standard softmax-based classifiers as unnormalized log-densities of the data distribution and show that input-gradients can be viewed as gradients of a class-conditional generative model $p_{\theta}(\mathbf{x} \mid y)$ implicit in the discriminative model. This leads us to hypothesize that the highly structured and explanatory nature of input-gradients may be due to the alignment of this class-conditional model $p_{\theta}(\mathbf{x} \mid y)$ with that of the ground truth data distribution $p_{\text{data}} (\mathbf{x} \mid y)$. We test this hypothesis by studying the effect of density alignment on gradient explanations. To achieve this density alignment, we use an algorithm called score-matching, and propose novel approximations to this algorithm to enable training large-scale models. Our experiments show that improving the alignment of the implicit density model with the data distribution enhances gradient structure and explanatory power while reducing this alignment has the opposite effect. This also leads us to conjecture that unintended density alignment in standard neural network training may explain the highly structured nature of input-gradients observed in practice. Overall, our finding that input-gradients capture information regarding an implicit generative model implies that we need to re-think their use for interpreting discriminative models.
Jonathan Gray, Adam Lerer, Anton Bakhtin, Noam Brown
tl;dr: We present an agent that approximates a one-step equilibrium in no-press Diplomacy using no-regret learning and show that it exceeds human-level performance
Prior AI breakthroughs in complex games have focused on either the purely adversarial or purely cooperative settings. In contrast, Diplomacy is a game of shifting alliances that involves both cooperation and competition. For this reason, Diplomacy has proven to be a formidable research challenge. In this paper we describe an agent for the no-press variant of Diplomacy that combines supervised learning on human data with one-step lookahead search via regret minimization. Regret minimization techniques have been behind previous AI successes in adversarial games, most notably poker, but have not previously been shown to be successful in large-scale games involving cooperation. We show that our agent greatly exceeds the performance of past no-press Diplomacy bots, is unexploitable by expert humans, and ranks in the top 2% of human players when playing anonymous games on a popular Diplomacy website.
Jeff Donahue, Sander Dieleman, Mikolaj Binkowski, Erich Elsen, Karen Simonyan
tl;dr: Efficient, adversarially trained feed-forward text-to-speech model producing high-quality speech, learnt end-to-end in a single stage.
Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from normalised text or phonemes in an end-to-end manner, resulting in models which operate directly on character or phoneme input sequences and produce raw speech audio outputs. Our proposed generator is feed-forward and thus efficient for both training and inference, using a differentiable alignment scheme based on token length prediction. It learns to produce high fidelity audio through a combination of adversarial feedback and prediction losses constraining the generated audio to roughly match the ground truth in terms of its total duration and mel-spectrogram. To allow the model to capture temporal variation in the generated audio, we employ soft dynamic time warping in the spectrogram-based prediction loss. The resulting model achieves a mean opinion score exceeding 4 on a 5 point scale, which is comparable to the state-of-the-art models relying on multi-stage training and additional supervision.
Avi Singh, Huihan Liu, Gaoyue Zhou, Albert Yu, Nicholas Rhinehart, Sergey Levine
tl;dr: We propose a method for pre-training a prior for reinforcement learning using data from a diverse range of tasks, and use this prior to speed up learning of new tasks.
Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language processing or computer vision, pre-training on large, previously collected datasets to bootstrap learning for new tasks has emerged as a powerful paradigm to reduce data requirements when learning a new task. In this paper, we ask the following question: how can we enable similarly useful pre-training for RL agents? We propose a method for pre-training behavioral priors that can capture complex input-output relationships observed in successful trials from a wide range of previously seen tasks, and we show how this learned prior can be used for rapidly learning new tasks without impeding the RL agent's ability to try out novel behaviors. We demonstrate the effectiveness of our approach in challenging robotic manipulation domains involving image observations and sparse reward functions, where our method outperforms prior works by a substantial margin. Additional materials can be found on our project website:
Cheng Lu, Jianfei Chen, Chongxuan Li, Qiuhao Wang, Jun Zhu
tl;dr: We generalize normalizing flows, allowing the mapping to be implicitly defined by the roots of an equation and enlarging the expressiveness power while retaining the tractability.
Normalizing flows define a probability distribution by an explicit invertible transformation $\boldsymbol{\mathbf{z}}=f(\boldsymbol{\mathbf{x}})$. In this work, we present implicit normalizing flows (ImpFlows), which generalize normalizing flows by allowing the mapping to be implicitly defined by the roots of an equation $F(\boldsymbol{\mathbf{z}}, \boldsymbol{\mathbf{x}})= \boldsymbol{\mathbf{0}}$. ImpFlows build on residual flows (ResFlows) with a proper balance between expressiveness and tractability. Through theoretical analysis, we show that the function space of ImpFlow is strictly richer than that of ResFlows. Furthermore, for any ResFlow with a fixed number of blocks, there exists some function that ResFlow has a non-negligible approximation error. However, the function is exactly representable by a single-block ImpFlow. We propose a scalable algorithm to train and draw samples from ImpFlows. Empirically, we evaluate ImpFlow on several classification and density modeling tasks, and ImpFlow outperforms ResFlow with a comparable amount of parameters on all the benchmarks.
Anirudh Goyal, Alex Lamb, Jordan Hoffmann, Shagun Sodhani, Sergey Levine, Yoshua Bengio, Bernhard Schölkopf
tl;dr: Learning recurrent mechanisms which operate independently, and sparingly interact can lead to better generalization to out of distribution samples.
We explore the hypothesis that learning modular structures which reflect the dynamics of the environment can lead to better generalization and robustness to changes that only affect a few of the underlying causes. We propose Recurrent Independent Mechanisms (RIMs), a new recurrent architecture in which multiple groups of recurrent cells operate with nearly independent transition dynamics, communicate only sparingly through the bottleneck of attention, and compete with each other so they are updated only at time steps where they are most relevant. We show that this leads to specialization amongst the RIMs, which in turn allows for remarkably improved generalization on tasks where some factors of variation differ systematically between training and evaluation.
Huy Tuan Pham, Phan-Minh Nguyen
tl;dr: We propose a rigorous framework for three-layer neural networks in the mean field regime and prove a global convergence guarantee.
In the mean field regime, neural networks are appropriately scaled so that as the width tends to infinity, the learning dynamics tends to a nonlinear and nontrivial dynamical limit, known as the mean field limit. This lends a way to study large-width neural networks via analyzing the mean field limit. Recent works have successfully applied such analysis to two-layer networks and provided global convergence guarantees. The extension to multilayer ones however has been a highly challenging puzzle, and little is known about the optimization efficiency in the mean field regime when there are more than two layers. In this work, we prove a global convergence result for unregularized feedforward three-layer networks in the mean field regime. We first develop a rigorous framework to establish the mean field limit of three-layer networks under stochastic gradient descent training. To that end, we propose the idea of a neuronal embedding, which comprises of a fixed probability space that encapsulates neural networks of arbitrary sizes. The identified mean field limit is then used to prove a global convergence guarantee under suitable regularity and convergence mode assumptions, which – unlike previous works on two-layer networks – does not rely critically on convexity. Underlying the result is a universal approximation property, natural of neural networks, which importantly is shown to hold at any finite training time (not necessarily at convergence) via an algebraic topology argument.
Sameera Ramasinghe, Kanchana Nisal Ranasinghe, Salman Khan, Nick Barnes, Stephen Gould
tl;dr: Conditional generation in continuous multimodal spaces by learning the behavior of latent variables.
Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings. We propose a novel general-purpose framework for conditional generation in multimodal spaces, that uses latent variables to model generalizable learning patterns while minimizing a family of regression cost functions. At inference, the latent variables are optimized to find solutions corresponding to multiple output modes. Compared to existing generative solutions, our approach demonstrates faster and more stable convergence, and can learn better representations for downstream tasks. Importantly, it provides a simple generic model that can perform better than highly engineered pipelines tailored using domain expertise on a variety of tasks, while generating diverse outputs. Code available at
Felix Hill, Olivier Tieleman, Tamara von Glehn, Nathaniel Wong, Hamza Merzic, Stephen Clark
tl;dr: A language-learning agent with dual-coding external memory meta-learns to combine fast-mapped and semantic lexical knowledge to execute instructions in one-shot..
Recent work has shown that large text-based neural language models acquire a surprising propensity for one-shot learning. Here, we show that an agent situated in a simulated 3D world, and endowed with a novel dual-coding external memory, can exhibit similar one-shot word learning when trained with conventional RL algorithms. After a single introduction to a novel object via visual perception and language ("This is a dax"), the agent can manipulate the object as instructed ("Put the dax on the bed"), combining short-term, within-episode knowledge of the nonsense word with long-term lexical and motor knowledge. We find that, under certain training conditions and with a particular memory writing mechanism, the agent's one-shot word-object binding generalizes to novel exemplars within the same ShapeNet category, and is effective in settings with unfamiliar numbers of objects. We further show how dual-coding memory can be exploited as a signal for intrinsic motivation, stimulating the agent to seek names for objects that may be useful later. Together, the results demonstrate that deep neural networks can exploit meta-learning, episodic memory and an explicitly multi-modal environment to account for 'fast-mapping', a fundamental pillar of human cognitive development and a potentially transformative capacity for artificial agents.
Krzysztof Marcin Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Andreea Gane, Tamas Sarlos, Peter Hawkins, Jared Quincy Davis, Afroz Mohiuddin, Lukasz Kaiser, David Benjamin Belanger, Lucy J Colwell, Adrian Weller
tl;dr: We introduce Performers, linear full-rank-attention Transformers via provable random feature approximation methods, without relying on sparsity or low-rankness.
We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to quadratic) space and time complexity, without relying on any priors such as sparsity or low-rankness. To approximate softmax attention-kernels, Performers use a novel Fast Attention Via positive Orthogonal Random features approach (FAVOR+), which may be of independent interest for scalable kernel methods. FAVOR+ can also be used to efficiently model kernelizable attention mechanisms beyond softmax. This representational power is crucial to accurately compare softmax with other kernels for the first time on large-scale tasks, beyond the reach of regular Transformers, and investigate optimal attention-kernels. Performers are linear architectures fully compatible with regular Transformers and with strong theoretical guarantees: unbiased or nearly-unbiased estimation of the attention matrix, uniform convergence and low estimation variance. We tested Performers on a rich set of tasks stretching from pixel-prediction through text models to protein sequence modeling. We demonstrate competitive results with other examined efficient sparse and dense attention methods, showcasing effectiveness of the novel attention-learning paradigm leveraged by Performers.
Dibya Ghosh, Abhishek Gupta, Ashwin Reddy, Justin Fu, Coline Manon Devin, Benjamin Eysenbach, Sergey Levine
tl;dr: We present GCSL, a simple RL method that uses supervised learning to learn goal-reaching policies.
Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study RL algorithms that use imitation learning to acquire goal reaching policies from scratch, without the need for expert demonstrations or a value function. In lieu of demonstrations, we leverage the property that any trajectory is a successful demonstration for reaching the final state in that same trajectory. We propose a simple algorithm in which an agent continually relabels and imitates the trajectories it generates to progressively learn goal-reaching behaviors from scratch. Each iteration, the agent collects new trajectories using the latest policy, and maximizes the likelihood of the actions along these trajectories under the goal that was actually reached, so as to improve the policy. We formally show that this iterated supervised learning procedure optimizes a bound on the RL objective, derive performance bounds of the learned policy, and empirically demonstrate improved goal-reaching performance and robustness over current RL algorithms in several benchmark tasks.
Akinori F Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka
tl;dr: With a novel sequential density estimation algorithm, we relax critical assumptions of the classical Sequential Probability Ratio Test to be applicable in various real-world scenarios.
Classifying sequential data as early and as accurately as possible is a challenging yet critical problem, especially when a sampling cost is high. One algorithm that achieves this goal is the sequential probability ratio test (SPRT), which is known as Bayes-optimal: it can keep the expected number of data samples as small as possible, given the desired error upper-bound. However, the original SPRT makes two critical assumptions that limit its application in real-world scenarios: (i) samples are independently and identically distributed, and (ii) the likelihood of the data being derived from each class can be calculated precisely. Here, we propose the SPRT-TANDEM, a deep neural network-based SPRT algorithm that overcomes the above two obstacles. The SPRT-TANDEM sequentially estimates the log-likelihood ratio of two alternative hypotheses by leveraging a novel Loss function for Log-Likelihood Ratio estimation (LLLR) while allowing correlations up to $N (\in \mathbb{N})$ preceding samples. In tests on one original and two public video databases, Nosaic MNIST, UCF101, and SiW, the SPRT-TANDEM achieves statistically significantly better classification accuracy than other baseline classifiers, with a smaller number of data samples. The code and Nosaic MNIST are publicly available at
Pedro Hermosilla, Marco Schäfer, Matej Lang, Gloria Fackelmann, Pere-Pau Vázquez, Barbora Kozlikova, Michael Krone, Tobias Ritschel, Timo Ropinski
tl;dr: We present a new neural network architecture to process 3D protein structures.
Proteins perform a large variety of functions in living organisms and thus play a key role in biology. However, commonly used algorithms in protein representation learning were not specifically designed for protein data, and are therefore not able to capture all relevant structural levels of a protein during learning. To fill this gap, we propose two new learning operators, specifically designed to process protein structures. First, we introduce a novel convolution operator that considers the primary, secondary, and tertiary structure of a protein by using $n$-D convolutions defined on both the Euclidean distance, as well as multiple geodesic distances between the atoms in a multi-graph. Second, we introduce a set of hierarchical pooling operators that enable multi-scale protein analysis. We further evaluate the accuracy of our algorithms on common downstream tasks, where we outperform state-of-the-art protein learning algorithms.
Muhammad Khalifa, Hady Elsahar, Marc Dymetman
tl;dr: We propose a novel approach to Controlled NLG, relying on Constraints over Distributions, Information Geometry, and Sampling from Energy-Based Models.
We propose a Distributional Approach for addressing Controlled Text Generation from pre-trained Language Models (LM). This approach permits to specify, in a single formal framework, both “pointwise’” and “distributional” constraints over the target LM — to our knowledge, the first model with such generality —while minimizing KL divergence from the initial LM distribution. The optimal target distribution is then uniquely determined as an explicit EBM (Energy-BasedModel) representation. From that optimal representation, we then train a target controlled Autoregressive LM through an adaptive distributional variant of PolicyGradient. We conduct a first set of experiments over pointwise constraints showing the advantages of our approach over a set of baselines, in terms of obtaining a controlled LM balancing constraint satisfaction with divergence from the pretrained LM. We then perform experiments over distributional constraints, a unique feature of our approach, demonstrating its potential as a remedy to the problem of Bias in Language Models. Through an ablation study, we show the effectiveness of our adaptive technique for obtaining faster convergence. Code available at
John D Co-Reyes, Yingjie Miao, Daiyi Peng, Esteban Real, Quoc V Le, Sergey Levine, Honglak Lee, Aleksandra Faust
tl;dr: We meta-learn RL algorithms by evolving computational graphs which compute the loss function for a value-based model-free RL agent to optimize.
We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. Our method can both learn from scratch and bootstrap off known existing algorithms, like DQN, enabling interpretable modifications which improve performance. Learning from scratch on simple classical control and gridworld tasks, our method rediscovers the temporal-difference (TD) algorithm. Bootstrapped from DQN, we highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games. The analysis of the learned algorithm behavior shows resemblance to recently proposed RL algorithms that address overestimation in value-based methods.
Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, Trevor Darrell
tl;dr: Deep networks can generalize better during testing by adapting to feedback from their own predictions.
A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions. Our method estimates normalization statistics and optimizes channel-wise affine transformations to update online on each batch. Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. Tent handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark. These results are achieved in one epoch of test-time optimization without altering training.
Naichen Shi, Dawei Li, Mingyi Hong, Ruoyu Sun
Despite the existence of divergence examples, RMSprop remains one of the most popular algorithms in machine learning. Towards closing the gap between theory and practice, we prove that RMSprop converges with proper choice of hyper-parameters under certain conditions. More specifically, we prove that when the hyper-parameter $\beta_2$ is close enough to $1$, RMSprop and its random shuffling version converge to a bounded region in general, and to critical points in the interpolation regime. It is worth mentioning that our results do not depend on ``bounded gradient" assumption, which is often the key assumption utilized by existing theoretical work for Adam-type adaptive gradient method. Removing this assumption allows us to establish a phase transition from divergence to non-divergence for RMSprop. Finally, based on our theory, we conjecture that in practice there is a critical threshold $\sf{\beta_2^*}$, such that RMSprop generates reasonably good results only if $1>\beta_2\ge \sf{\beta_2^*}$. We provide empirical evidence for such a phase transition in our numerical experiments.
Yuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao, Yinan Zhang, Antonio Torralba, Sanja Fidler
tl;dr: We marry generative models with differentiable rendering to extract and disentangle 3D knowledge learned implicitly by generative image synthesis models
Differentiable rendering has paved the way to training neural networks to perform “inverse graphics” tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on multi-view imagery which are not readily available in practice. Recent Generative Adversarial Networks (GANs) that synthesize images, in contrast, seem to acquire 3D knowledge implicitly during training: object viewpoints can be manipulated by simply manipulating the latent codes. However, these latent codes often lack further physical interpretation and thus GANs cannot easily be inverted to perform explicit 3D reasoning. In this paper, we aim to extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers. Key to our approach is to exploit GANs as a multi-view data generator to train an inverse graphics network using an off-the-shelf differentiable renderer, and the trained inverse graphics network as a teacher to disentangle the GAN's latent code into interpretable 3D properties. The entire architecture is trained iteratively using cycle consistency losses. We show that our approach significantly outperforms state-of-the-art inverse graphics networks trained on existing datasets, both quantitatively and via user studies. We further showcase the disentangled GAN as a controllable 3D “neural renderer", complementing traditional graphics renderers.
Gege Qi, Lijun GONG, Yibing Song, Kai Ma, Yefeng Zheng
tl;dr: We propose a stabilized adversarial attack method for medical image analysis.
Convolutional Neural Networks (CNNs) have advanced existing medical systems for automatic disease diagnosis. However, a threat to these systems arises that adversarial attacks make CNNs vulnerable. Inaccurate diagnosis results make a negative influence on human healthcare. There is a need to investigate potential adversarial attacks to robustify deep medical diagnosis systems. On the other side, there are several modalities of medical images (e.g., CT, fundus, and endoscopic image) of which each type is significantly different from others. It is more challenging to generate adversarial perturbations for different types of medical images. In this paper, we propose an image-based medical adversarial attack method to consistently produce adversarial perturbations on medical images. The objective function of our method consists of a loss deviation term and a loss stabilization term. The loss deviation term increases the divergence between the CNN prediction of an adversarial example and its ground truth label. Meanwhile, the loss stabilization term ensures similar CNN predictions of this example and its smoothed input. From the perspective of the whole iterations for perturbation generation, the proposed loss stabilization term exhaustively searches the perturbation space to smooth the single spot for local optimum escape. We further analyze the KL-divergence of the proposed loss function and find that the loss stabilization term makes the perturbations updated towards a fixed objective spot while deviating from the ground truth. This stabilization ensures the proposed medical attack effective for different types of medical images while producing perturbations in small variance. Experiments on several medical image analysis benchmarks including the recent COVID-19 dataset show the stability of the proposed method.
Anand Gopalakrishnan, Sjoerd van Steenkiste, Jürgen Schmidhuber
tl;dr: We propose PermaKey, a novel method for learning object keypoint representations that leverages local predictability as a measure of objectness.
We propose PermaKey, a novel approach to representation learning based on object keypoints. It leverages the predictability of local image regions from spatial neighborhoods to identify salient regions that correspond to object parts, which are then converted to keypoints. Unlike prior approaches, it utilizes predictability to discover object keypoints, an intrinsic property of objects. This ensures that it does not overly bias keypoints to focus on characteristics that are not unique to objects, such as movement, shape, colour etc. We demonstrate the efficacy of PermaKey on Atari where it learns keypoints corresponding to the most salient object parts and is robust to certain visual distractors. Further, on downstream RL tasks in the Atari domain we demonstrate how agents equipped with our keypoints outperform those using competing alternatives, even on challenging environments with moving backgrounds or distractor objects.
Zhengxian Lin, Kin-Ho Lam, Alan Fern
tl;dr: We introduced the embedded self-prediction (ESP) model for producing meaningful and sound contrastive explanations for RL agents.
We investigate a deep reinforcement learning (RL) architecture that supports explaining why a learned agent prefers one action over another. The key idea is to learn action-values that are directly represented via human-understandable properties of expected futures. This is realized via the embedded self-prediction (ESP) model, which learns said properties in terms of human provided features. Action preferences can then be explained by contrasting the future properties predicted for each action. To address cases where there are a large number of features, we develop a novel method for computing minimal sufficient explanations from an ESP. Our case studies in three domains, including a complex strategy game, show that ESP models can be effectively learned and support insightful explanations.
Max B Paulus, Chris J. Maddison, Andreas Krause
tl;dr: We reduce the variance of the straight-through Gumbel-Softmax estimator to improve its performance.
Gradient estimation in models with discrete latent variables is a challenging problem, because the simplest unbiased estimators tend to have high variance. To counteract this, modern estimators either introduce bias, rely on multiple function evaluations, or use learned, input-dependent baselines. Thus, there is a need for estimators that require minimal tuning, are computationally cheap, and have low mean squared error. In this paper, we show that the variance of the straight-through variant of the popular Gumbel-Softmax estimator can be reduced through Rao-Blackwellization without increasing the number of function evaluations. This provably reduces the mean squared error. We empirically demonstrate that this leads to variance reduction, faster convergence, and generally improved performance in two unsupervised latent variable models.
Siyi Hu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang
Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task. The limitation is due to the restricted model architecture related to fixed input and output dimensions. This hinders the experience accumulation and transfer of the learned agent over tasks with diverse levels of difficulty (e.g. 3 vs 3 or 5 vs 6 multi-agent games). In this paper, we make the first attempt to explore a universal multi-agent reinforcement learning pipeline, designing one single architecture to fit tasks with the requirement of different observation and action configurations. Unlike previous RNN-based models, we utilize a transformer-based model to generate a flexible policy by decoupling the policy distribution from the intertwined input observation with an importance weight measured by the merits of the self-attention mechanism. Compared to a standard transformer block, the proposed model, named as Universal Policy Decoupling Transformer (UPDeT), further relaxes the action restriction and makes the multi-agent task's decision process more explainable. UPDeT is general enough to be plugged into any multi-agent reinforcement learning pipeline and equip them with strong generalization abilities that enables the handling of multiple tasks at a time. Extensive experiments on large-scale SMAC multi-agent competitive games demonstrate that the proposed UPDeT-based multi-agent reinforcement learning achieves significant results relative to state-of-the-art approaches, demonstrating advantageous transfer capability in terms of both performance and training speed (10 times faster).
Cheng Perng Phoo, Bharath Hariharan
tl;dr: Self-training a source domain classifier on unlabeled data from the target domain improves cross-domain few-shot transfer.
Most few-shot learning techniques are pre-trained on a large, labeled “base dataset”. In problem domains where such large labeled datasets are not available for pre-training (e.g., X-ray, satellite images), one must resort to pre-training in a different “source” problem domain (e.g., ImageNet), which can be very different from the desired target task. Traditional few-shot and transfer learning techniques fail in the presence of such extreme differences between the source and target tasks. In this paper, we present a simple and effective solution to tackle this extreme domain gap: self-training a source domain representation on unlabeled data from the target domain. We show that this improves one-shot performance on the target domain by 2.9 points on average on the challenging BSCD-FSL benchmark consisting of datasets from multiple domains.
Guan-Horng Liu, Tianrong Chen, Evangelos Theodorou
tl;dr: We introduce a new class of optimal-control-theoretic training methods, DDPNOpt, that performs a distinct backward pass inherited with Bellman optimality and generates layer-wise feedback policies to robustify training over existing training methods
Interpretation of Deep Neural Networks (DNNs) training as an optimal control problem with nonlinear dynamical systems has received considerable attention recently, yet the algorithmic development remains relatively limited. In this work, we make an attempt along this line by reformulating the training procedure from the trajectory optimization perspective. We first show that most widely-used algorithms for training DNNs can be linked to the Differential Dynamic Programming (DDP), a celebrated second-order method rooted in the Approximate Dynamic Programming. In this vein, we propose a new class of optimizer, DDP Neural Optimizer (DDPNOpt), for training feedforward and convolution networks. DDPNOpt features layer-wise feedback policies which improve convergence and reduce sensitivity to hyper-parameter over existing methods. It outperforms other optimal-control inspired training methods in both convergence and complexity, and is competitive against state-of-the-art first and second order methods. We also observe DDPNOpt has surprising benefit in preventing gradient vanishing. Our work opens up new avenues for principled algorithmic design built upon the optimal control theory.
Konstantin-Klemens Lurz, Mohammad Bashiri, Konstantin Willeke, Akshay Jagadish, Eric Wang, Edgar Y. Walker, Santiago A Cadena, Taliah Muhammad, Erick Cobos, Andreas S. Tolias, Alexander S Ecker, Fabian H. Sinz
tl;dr: We introduce a novel network architecture which sets a new state of the art at predicting neural responses to visual input and successfully learns generalizing features of mouse visual cortex (V1).
Deep neural networks (DNN) have set new standards at predicting responses of neural populations to visual input. Most such DNNs consist of a convolutional network (core) shared across all neurons which learns a representation of neural computation in visual cortex and a neuron-specific readout that linearly combines the relevant features in this representation. The goal of this paper is to test whether such a representation is indeed generally characteristic for visual cortex, i.e. generalizes between animals of a species, and what factors contribute to obtaining such a generalizing core. To push all non-linear computations into the core where the generalizing cortical features should be learned, we devise a novel readout that reduces the number of parameters per neuron in the readout by up to two orders of magnitude compared to the previous state-of-the-art. It does so by taking advantage of retinotopy and learns a Gaussian distribution over the neuron’s receptive field position. With this new readout we train our network on neural responses from mouse primary visual cortex (V1) and obtain a gain in performance of 7% compared to the previous state-of-the-art network. We then investigate whether the convolutional core indeed captures general cortical features by using the core in transfer learning to a different animal. When transferring a core trained on thousands of neurons from various animals and scans we exceed the performance of training directly on that animal by 12%, and outperform a commonly used VGG16 core pre-trained on imagenet by 33%. In addition, transfer learning with our data-driven core is more data-efficient than direct training, achieving the same performance with only 40% of the data. Our model with its novel readout thus sets a new state-of-the-art for neural response prediction in mouse visual cortex from natural images, generalizes between animals, and captures better characteristic cortical features than current task-driven pre-training approaches such as VGG16.
Chenlin Meng, Jiaming Song, Yang Song, Shengjia Zhao, Stefano Ermon
While autoregressive models excel at image compression, their sample quality is often lacking. Although not realistic, generated images often have high likelihood according to the model, resembling the case of adversarial examples. Inspired by a successful adversarial defense method, we incorporate randomized smoothing into autoregressive generative modeling. We first model a smoothed version of the data distribution, and then reverse the smoothing process to recover the original data distribution. This procedure drastically improves the sample quality of existing autoregressive models on several synthetic and real-world image datasets while obtaining competitive likelihoods on synthetic datasets.
Yang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia, Xingjun Ma, Yisen Wang
tl;dr: Training with Channel-wise Activation Suppressing (CAS) can help imrove the robustness of adversarial training.
The study of adversarial examples and their activations have attracted significant attention for secure and robust learning with deep neural networks (DNNs). Different from existing works, in this paper, we highlight two new characteristics of adversarial examples from the channel-wise activation perspective: 1) the activation magnitudes of adversarial examples are higher than that of natural examples; and 2) the channels are activated more uniformly by adversarial examples than natural examples. We find that, while the state-of-the-art defense adversarial training has addressed the first issue of high activation magnitude via training on adversarial examples, the second issue of uniform activation remains. This motivates us to suppress redundant activations from being activated by adversarial perturbations during the adversarial training process, via a Channel-wise Activation Suppressing (CAS) training strategy. We show that CAS can train a model that inherently suppresses adversarial activations, and can be easily applied to existing defense methods to further improve their robustness. Our work provides a simplebut generic training strategy for robustifying the intermediate layer activations of DNNs.
Zhengyang Geng, Meng-Hao Guo, Hongxu Chen, Xia Li, Ke Wei, Zhouchen Lin
As an essential ingredient of modern deep learning, attention mechanism, especially self-attention, plays a vital role in the global correlation discovery. However, is hand-crafted attention irreplaceable when modeling the global context? Our intriguing finding is that self-attention is not better than the matrix decomposition~(MD) model developed 20 years ago regarding the performance and computational cost for encoding the long-distance dependencies. We model the global context issue as a low-rank completion problem and show that its optimization algorithms can help design global information blocks. This paper then proposes a series of Hamburgers, in which we employ the optimization algorithms for solving MDs to factorize the input representations into sub-matrices and reconstruct a low-rank embedding. Hamburgers with different MDs can perform favorably against the popular global context module self-attention when carefully coping with gradients back-propagated through MDs. Comprehensive experiments are conducted in the vision tasks where it is crucial to learn the global context, including semantic segmentation and image generation, demonstrating significant improvements over self-attention and its variants. Code is available at
Rizal Fathony, Anit Kumar Sahu, Devin Willmott, J Zico Kolter
Although deep networks are typically used to approximate functions over high dimensional inputs, recent work has increased interest in neural networks as function approximators for low-dimensional-but-complex functions, such as representing images as a function of pixel coordinates, solving differential equations, or representing signed distance fields or neural radiance fields. Key to these recent successes has been the use of new elements such as sinusoidal nonlinearities, or Fourier features in positional encodings, which vastly outperform simple ReLU networks. In this paper, we propose and empirically demonstrate that an arguably simpler class of function approximators can work just as well for such problems: multiplicative filter networks. In these networks, we avoid traditional compositional depth altogether, and simply multiply together (linear functions of) sinusoidal or Gabor wavelet functions applied to the input. This representation has the notable advantage that the entire function can simply be viewed as a linear function approximator over an exponential number of Fourier or Gabor basis functions, respectively. Despite this simplicity, when compared to recent approaches that use Fourier features with ReLU networks or sinusoidal activation networks, we show that these multiplicative filter networks largely outperform or match the performance of these recent approaches on the domains highlighted in these past works.
Mandela Patrick, Po-Yao Huang, Yuki Asano, Florian Metze, Alexander G Hauptmann, Joao F. Henriques, Andrea Vedaldi
tl;dr: We use a generative objective to improve the instance discrimination limitations of contrastive learning to set new state-of-the-art results in text-to-video retrieval
The dominant paradigm for learning video-text representations – noise contrastive learning – increases the similarity of the representations of pairs of samples that are known to be related, such as text and video from the same sample, and pushes away the representations of all other pairs. We posit that this last behaviour is too strict, enforcing dissimilar representations even for samples that are semantically-related – for example, visually similar videos or ones that share the same depicted action. In this paper, we propose a novel method that alleviates this by leveraging a generative model to naturally push these related samples together: each sample’s caption must be reconstructed as a weighted combination of a support set of visual representations. This simple idea ensures that representations are not overly-specialized to individual samples, are reusable across the dataset, and results in representations that explicitly encode semantics shared between samples, unlike noise contrastive learning. Our proposed method outperforms others by a large margin on MSR-VTT, VATEX, ActivityNet, and MSVD for video-to-text and text-to-video retrieval.
Matan Atzmon, Yaron Lipman
tl;dr: Sign agnostic learning with derivatives for learning high fidelity 3D implicit neural representations shape space from raw data.
Learning 3D geometry directly from raw data, such as point clouds, triangle soups, or unoriented meshes is still a challenging task that feeds many downstream computer vision and graphics applications. In this paper, we introduce SALD: a method for learning implicit neural representations of shapes directly from raw data. We generalize sign agnostic learning (SAL) to include derivatives: given an unsigned distance function to the input raw data, we advocate a novel sign agnostic regression loss, incorporating both pointwise values and gradients of the unsigned distance function. Optimizing this loss leads to a signed implicit function solution, the zero level set of which is a high quality and valid manifold approximation to the input 3D data. The motivation behind SALD is that incorporating derivatives in a regression loss leads to a lower sample complexity, and consequently better fitting. In addition, we provide empirical evidence, as well as theoretical motivation in 2D that SAL enjoys a minimal surface property, favoring minimal area solutions. More importantly, we are able to show that this property still holds for SALD, i.e., with derivatives included. We demonstrate the efficacy of SALD for shape space learning on two challenging datasets: ShapeNet that contains inconsistent orientation and non-manifold meshes, and D-Faust that contains raw 3D scans (triangle soups). On both these datasets, we present state-of-the-art results.
Eli Ovits, Lior Wolf
tl;dr: A new loss for applying supervised deep learning to the problem of scheduling adiabatic quantum computations
Adiabatic quantum computation is a form of computation that acts by slowly interpolating a quantum system between an easy to prepare initial state and a final state that represents a solution to a given computational problem. The choice of the interpolation schedule is critical to the performance: if at a certain time point, the evolution is too rapid, the system has a high probability to transfer to a higher energy state, which does not represent a solution to the problem. On the other hand, an evolution that is too slow leads to a loss of computation time and increases the probability of failure due to decoherence. In this work, we train deep neural models to produce optimal schedules that are conditioned on the problem at hand. We consider two types of problem representation: the Hamiltonian form, and the Quadratic Unconstrained Binary Optimization (QUBO) form. A novel loss function that scores schedules according to their approximated success probability is introduced. We benchmark our approach on random QUBO problems, Grover search, 3-SAT, and MAX-CUT problems and show that our approach outperforms, by a sizable margin, the linear schedules as well as alternative approaches that were very recently proposed.
Glen Berseth, Daniel Geng, Coline Manon Devin, Nicholas Rhinehart, Chelsea Finn, Dinesh Jayaraman, Sergey Levine
tl;dr: Using Bayesian surprise as an unsupervised intrinsic reward function to learn complex behaviors in unstable environments.
Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche. We propose that such a struggle to achieve and preserve order might offer a principle for the emergence of useful behaviors in artificial agents. We formalize this idea into an unsupervised reinforcement learning method called surprise minimizing reinforcement learning (SMiRL). SMiRL alternates between learning a density model to evaluate the surprise of a stimulus, and improving the policy to seek more predictable stimuli. The policy seeks out stable and repeatable situations that counteract the environment's prevailing sources of entropy. This might include avoiding other hostile agents, or finding a stable, balanced pose for a bipedal robot in the face of disturbance forces. We demonstrate that our surprise minimizing agents can successfully play Tetris, Doom, control a humanoid to avoid falls, and navigate to escape enemies in a maze without any task-specific reward supervision. We further show that SMiRL can be used together with standard task rewards to accelerate reward-driven learning.
Aditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat, Himanshu Jain, Andreas Veit, Sanjiv Kumar
tl;dr: Adjusting classifier logits based on class priors, either post-hoc or during training, can improve performance on rare classes.
Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels have only a few associated samples. This poses a challenge for generalisation on such labels, and also makes naive learning biased towards dominant labels. In this paper, we present a statistical framework that unifies and generalises several recent proposals to cope with these challenges. Our framework revisits the classic idea of logit adjustment based on the label frequencies, which encourages a large relative margin between logits of rare positive versus dominant negative labels. This yields two techniques for long-tail learning, where such adjustment is either applied post-hoc to a trained model, or enforced in the loss during training. These techniques are statistically grounded, and practically effective on four real-world datasets with long-tailed label distributions.
Dong Bok Lee, Dongchan Min, Seanie Lee, Sung Ju Hwang
tl;dr: we propose a principled unsupervised meta-learning model which meta-learns a set-level variational posterior, by matching it with multi-modal prior distribution obtained by EM.
Unsupervised learning aims to learn meaningful representations from unlabeled data which can captures its intrinsic structure, that can be transferred to downstream tasks. Meta-learning, whose objective is to learn to generalize across tasks such that the learned model can rapidly adapt to a novel task, shares the spirit of unsupervised learning in that the both seek to learn more effective and efficient learning procedure than learning from scratch. The fundamental difference of the two is that the most meta-learning approaches are supervised, assuming full access to the labels. However, acquiring labeled dataset for meta-training not only is costly as it requires human efforts in labeling but also limits its applications to pre-defined task distributions. In this paper, we propose a principled unsupervised meta-learning model, namely Meta-GMVAE, based on Variational Autoencoder (VAE) and set-level variational inference. Moreover, we introduce a mixture of Gaussian (GMM) prior, assuming that each modality represents each class-concept in a randomly sampled episode, which we optimize with Expectation-Maximization (EM). Then, the learned model can be used for downstream few-shot classification tasks, where we obtain task-specific parameters by performing semi-supervised EM on the latent representations of the support and query set, and predict labels of the query set by computing aggregated posteriors. We validate our model on Omniglot and Mini-ImageNet datasets by evaluating its performance on downstream few-shot classification tasks. The results show that our model obtain impressive performance gains over existing unsupervised meta-learning baselines, even outperforming supervised MAML on a certain setting.
Karan Goel, Albert Gu, Yixuan Li, Christopher Re
tl;dr: We describe how to fix classifiers that fail on subgroups of a class using a combination of learned data augmentation & consistency training to achieve subgroup invariance.
Classifiers in machine learning are often brittle when deployed. Particularly concerning are models with inconsistent performance on specific subgroups of a class, e.g., exhibiting disparities in skin cancer classification in the presence or absence of a spurious bandage. To mitigate these performance differences, we introduce model patching, a two-stage framework for improving robustness that encourages the model to be invariant to subgroup differences, and focus on class information shared by subgroups. Model patching first models subgroup features within a class and learns semantic transformations between them, and then trains a classifier with data augmentations that deliberately manipulate subgroup features. We instantiate model patching with CAMEL, which (1) uses a CycleGAN to learn the intra-class, inter-subgroup augmentations, and (2) balances subgroup performance using a theoretically-motivated subgroup consistency regularizer, accompanied by a new robust objective. We demonstrate CAMEL’s effectiveness on 3 benchmark datasets, with reductions in robust error of up to 33% relative to the best baseline. Lastly, CAMEL successfully patches a model that fails due to spurious features on a real-world skin cancer dataset.
Kenji Kawaguchi
tl;dr: We analyze gradient dynamics of a simple deep equilibrium model and mathematically prove its theoretical properties.
A deep equilibrium model uses implicit layers, which are implicitly defined through an equilibrium point of an infinite sequence of computation. It avoids any explicit computation of the infinite sequence by finding an equilibrium point directly via root-finding and by computing gradients via implicit differentiation. In this paper, we analyze the gradient dynamics of deep equilibrium models with nonlinearity only on weight matrices and non-convex objective functions of weights for regression and classification. Despite non-convexity, convergence to global optimum at a linear rate is guaranteed without any assumption on the width of the models, allowing the width to be smaller than the output dimension and the number of data points. Moreover, we prove a relation between the gradient dynamics of the deep implicit layer and the dynamics of trust region Newton method of a shallow explicit layer. This mathematically proven relation along with our numerical observation suggests the importance of understanding implicit bias of implicit layers and an open problem on the topic. Our proofs deal with implicit layers, weight tying and nonlinearity on weights, and differ from those in the related literature.
Xiu Su, Shan You, Tao Huang, Fei Wang, Chen Qian, Changshui Zhang, Chang Xu
tl;dr: One-shot locally free weight sharing supernet for searching optimal network width
Searching for network width is an effective way to slim deep neural networks with hardware budgets. With this aim, a one-shot supernet is usually leveraged as a performance evaluator to rank the performance \wrt~different width. Nevertheless, current methods mainly follow a manually fixed weight sharing pattern, which is limited to distinguish the performance gap of different width. In this paper, to better evaluate each width, we propose a locally free weight sharing strategy (CafeNet) accordingly. In CafeNet, weights are more freely shared, and each width is jointly indicated by its base channels and free channels, where free channels are supposed to locate freely in a local zone to better represent each width. Besides, we propose to further reduce the search space by leveraging our introduced FLOPs-sensitive bins. As a result, our CafeNet can be trained stochastically and get optimized within a min-min strategy. Extensive experiments on ImageNet, CIFAR-10, CelebA and MS COCO dataset have verified our superiority comparing to other state-of-the-art baselines. For example, our method can further boost the benchmark NAS network EfficientNet-B0 by 0.41\% via searching its width more delicately.
Zhiyuan Li, Yi Zhang, Sanjeev Arora
tl;dr: We construct a single natural distribution on which any fully-connected networks trained with SGD requires \Omega(d^2) samples to generalize while O (1) samples suffices for convolutional architectures.
Convolutional neural networks often dominate fully-connected counterparts in generalization performance, especially on image classification tasks. This is often explained in terms of \textquotedblleft better inductive bias.\textquotedblright\ However, this has not been made mathematically rigorous, and the hurdle is that the sufficiently wide fully-connected net can always simulate the convolutional net. Thus the training algorithm plays a role. The current work describes a natural task on which a provable sample complexity gap can be shown, for standard training algorithms. We construct a single natural distribution on $\mathbb{R}^d\times\{\pm 1\}$ on which any orthogonal-invariant algorithm (i.e. fully-connected networks trained with most gradient-based methods from gaussian initialization) requires $\Omega(d^2)$ samples to generalize while $O(1)$ samples suffice for convolutional architectures. Furthermore, we demonstrate a single target function, learning which on all possible distributions leads to an $O(1)$ vs $\Omega(d^2/\varepsilon)$ gap. The proof relies on the fact that SGD on fully-connected network is orthogonal equivariant. Similar results are achieved for $\ell_2$ regression and adaptive training algorithms, e.g. Adam and AdaGrad, which are only permutation equivariant.
Andrii Zadaianchuk, Maximilian Seitzer, Georg Martius
tl;dr: The combination of object-centric representations and goal-conditioned attention policies helps autonomous agents to learn useful multi-task policies in visual multi-object environments
Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal for an agent to discover new skills. Nevertheless, in compositional/multi-object environments it is difficult to disentangle all the factors of variation into such a fixed-length representation of the whole scene. We propose to use object-centric representations as a modular and structured observation space, which is learned with a compositional generative world model. We show that the structure in the representations in combination with goal-conditioned attention policies helps the autonomous agent to discover and learn useful skills. These skills can be further combined to address compositional tasks like the manipulation of several different objects.
Taiji Suzuki, Shunta Akiyama
Establishing a theoretical analysis that explains why deep learning can outperform shallow learning such as kernel methods is one of the biggest issues in the deep learning literature. Towards answering this question, we evaluate excess risk of a deep learning estimator trained by a noisy gradient descent with ridge regularization on a mildly overparameterized neural network, and discuss its superiority to a class of linear estimators that includes neural tangent kernel approach, random feature model, other kernel methods, $k$-NN estimator and so on. We consider a teacher-student regression model, and eventually show that {\it any} linear estimator can be outperformed by deep learning in a sense of the minimax optimal rate especially for a high dimension setting. The obtained excess bounds are so-called fast learning rate which is faster than $O(1/\sqrt{n})$ that is obtained by usual Rademacher complexity analysis. This discrepancy is induced by the non-convex geometry of the model and the noisy gradient descent used for neural network training provably reaches a near global optimal solution even though the loss landscape is highly non-convex. Although the noisy gradient descent does not employ any explicit or implicit sparsity inducing regularization, it shows a preferable generalization performance that dominates linear estimators.
Beidi Chen, Zichang Liu, Binghui Peng, Zhaozhuo Xu, Jonathan Lingjie Li, Tri Dao, Zhao Song, Anshumali Shrivastava, Christopher Re
tl;dr: We propose MONGOOSE, a learnable LSH framework for efficient neural network training.
Recent advances by practitioners in the deep learning community have breathed new life into Locality Sensitive Hashing (LSH), using it to reduce memory and time bottlenecks in neural network (NN) training. However, while LSH has sub-linear guarantees for approximate near-neighbor search in theory, it is known to have inefficient query time in practice due to its use of random hash functions. Moreover, when model parameters are changing, LSH suffers from update overhead. This work is motivated by an observation that model parameters evolve slowly, such that the changes do not always require an LSH update to maintain performance. This phenomenon points to the potential for a reduction in update time and allows for a modified learnable version of data-dependent LSH to improve query time at a low cost. We use the above insights to build MONGOOSE, an end-to-end LSH framework for efficient NN training. In particular, MONGOOSE is equipped with a scheduling algorithm to adaptively perform LSH updates with provable guarantees and learnable hash functions to improve query efficiency. Empirically, we validate MONGOOSE on large-scale deep learning models for recommendation systems and language modeling. We find that it achieves up to 8% better accuracy compared to previous LSH approaches, with $6.5 \times$ speed-up and $6\times$ reduction in memory usage.
Xin Yuan, Pedro Henrique Pamplona Savarese, Michael Maire
tl;dr: We propose an efficient training method that dynamically grows and prunes neural network architectures.
We develop an approach to growing deep network architectures over the course of training, driven by a principled combination of accuracy and sparsity objectives. Unlike existing pruning or architecture search techniques that operate on full-sized models or supernet architectures, our method can start from a small, simple seed architecture and dynamically grow and prune both layers and filters. By combining a continuous relaxation of discrete network structure optimization with a scheme for sampling sparse subnetworks, we produce compact, pruned networks, while also drastically reducing the computational expense of training. For example, we achieve $49.7\%$ inference FLOPs and $47.4\%$ training FLOPs savings compared to a baseline ResNet-50 on ImageNet, while maintaining $75.2\%$ top-1 validation accuracy --- all without any dedicated fine-tuning stage. Experiments across CIFAR, ImageNet, PASCAL VOC, and Penn Treebank, with convolutional networks for image classification and semantic segmentation, and recurrent networks for language modeling, demonstrate that we both train faster and produce more efficient networks than competing architecture pruning or search methods.
Sejun Park, Chulhee Yun, Jaeho Lee, Jinwoo Shin
tl;dr: We establish the tight bound on width for the universal approximability of neural network.
The universal approximation property of width-bounded networks has been studied as a dual of classical universal approximation results on depth-bounded networks. However, the critical width enabling the universal approximation has not been exactly characterized in terms of the input dimension $d_x$ and the output dimension $d_y$. In this work, we provide the first definitive result in this direction for networks using the ReLU activation functions: The minimum width required for the universal approximation of the $L^p$ functions is exactly $\max\{d_x+1,d_y\}$. We also prove that the same conclusion does not hold for the uniform approximation with ReLU, but does hold with an additional threshold activation function. Our proof technique can be also used to derive a tighter upper bound on the minimum width required for the universal approximation using networks with general activation functions.
Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur
tl;dr: Motivated by the connection between geometry of the loss landscape and generalization, we introduce a procedure for simultaneously minimizing loss value and loss sharpness.
In today's heavily overparameterized models, the value of the training loss provides few guarantees on model generalization ability. Indeed, optimizing only the training loss value, as is commonly done, can easily lead to suboptimal model quality. Motivated by the connection between geometry of the loss landscape and generalization---including a generalization bound that we prove here---we introduce a novel, effective procedure for instead simultaneously minimizing loss value and loss sharpness. In particular, our procedure, Sharpness-Aware Minimization (SAM), seeks parameters that lie in neighborhoods having uniformly low loss; this formulation results in a min-max optimization problem on which gradient descent can be performed efficiently. We present empirical results showing that SAM improves model generalization across a variety of benchmark datasets (e.g., CIFAR-{10, 100}, ImageNet, finetuning tasks) and models, yielding novel state-of-the-art performance for several. Additionally, we find that SAM natively provides robustness to label noise on par with that provided by state-of-the-art procedures that specifically target learning with noisy labels.
Yoav Levine, Barak Lenz, Opher Lieber, Omri Abend, Kevin Leyton-Brown, Moshe Tennenholtz, Yoav Shoham
tl;dr: Joint masking of correlated tokens significantly speeds up and improves BERT's pretraining
Masking tokens uniformly at random constitutes a common flaw in the pretraining of Masked Language Models (MLMs) such as BERT. We show that such uniform masking allows an MLM to minimize its training objective by latching onto shallow local signals, leading to pretraining inefficiency and suboptimal downstream performance. To address this flaw, we propose PMI-Masking, a principled masking strategy based on the concept of Pointwise Mutual Information (PMI), which jointly masks a token n-gram if it exhibits high collocation over the corpus. PMI-Masking motivates, unifies, and improves upon prior more heuristic approaches that attempt to address the drawback of random uniform token masking, such as whole-word masking, entity/phrase masking, and random-span masking. Specifically, we show experimentally that PMI-Masking reaches the performance of prior masking approaches in half the training time, and consistently improves performance at the end of pretraining.
Hanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey, Yisen Wang
tl;dr: We present a type of error-minimizing noise that can make training examples unlearnable to deep learning.
The volume of "free" data on the internet has been key to the current success of deep learning. However, it also raises privacy concerns about the unauthorized exploitation of personal data for training commercial models. It is thus crucial to develop methods to prevent unauthorized data exploitation. This paper raises the question: can data be made unlearnable for deep learning models? We present a type of error-minimizing noise that can indeed make training examples unlearnable. Error-minimizing noise is intentionally generated to reduce the error of one or more of the training example(s) close to zero, which can trick the model into believing there is "nothing" to learn from these example(s). The noise is restricted to be imperceptible to human eyes, and thus does not affect normal data utility. We empirically verify the effectiveness of error-minimizing noise in both sample-wise and class-wise forms. We also demonstrate its flexibility under extensive experimental settings and practicability in a case study of face recognition. Our work establishes an important first step towards making personal data unexploitable to deep learning models.
Zhiao Huang, Yuanming Hu, Tao Du, Siyuan Zhou, Hao Su, Joshua B. Tenenbaum, Chuang Gan
tl;dr: We propose a soft-body manipulation benchmark with differentiable physics support.
Simulated virtual environments serve as one of the main driving forces behind developing and evaluating skill learning algorithms. However, existing environments typically only simulate rigid body physics. Additionally, the simulation process usually does not provide gradients that might be useful for planning and control optimizations. We introduce a new differentiable physics benchmark called PasticineLab, which includes a diverse collection of soft body manipulation tasks. In each task, the agent uses manipulators to deform the plasticine into a desired configuration. The underlying physics engine supports differentiable elastic and plastic deformation using the DiffTaichi system, posing many under-explored challenges to robotic agents. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark. Experimental results suggest that 1) RL-based approaches struggle to solve most of the tasks efficiently; 2) gradient-based approaches, by optimizing open-loop control sequences with the built-in differentiable physics engine, can rapidly find a solution within tens of iterations, but still fall short on multi-stage tasks that require long-term planning. We expect that PlasticineLab will encourage the development of novel algorithms that combine differentiable physics and RL for more complex physics-based skill learning tasks. PlasticineLab will be made publicly available.
Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Jun Yuan, Orion Reblitz-Richardson
tl;dr: The padding mechanism in CNNs can induce harmful spatial bias in the learned weights and in the feature maps, which can be mitigated with careful architectural choices.
We show how feature maps in convolutional networks are susceptible to spatial bias. Due to a combination of architectural choices, the activation at certain locations is systematically elevated or weakened. The major source of this bias is the padding mechanism. Depending on several aspects of convolution arithmetic, this mechanism can apply the padding unevenly, leading to asymmetries in the learned weights. We demonstrate how such bias can be detrimental to certain tasks such as small object detection: the activation is suppressed if the stimulus lies in the impacted area, leading to blind spots and misdetection. We explore alternative padding methods and propose solutions for analyzing and mitigating spatial bias.
Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda
tl;dr: We propose Unbiased Teacher to jointly address the pseudo-labeling bias issue and the overfitting issue in semi-supervised object detection, and our model performs favorably against existing works on COCO-standard, COCO-additional, and VOC.
Semi-supervised learning, i.e., training networks with both labeled and unlabeled data, has made significant progress recently. However, existing works have primarily focused on image classification tasks and neglected object detection which requires more annotation effort. In this work, we revisit the Semi-Supervised Object Detection (SS-OD) and identify the pseudo-labeling bias issue in SS-OD. To address this, we introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner. Together with a class-balance loss to downweight overly confident pseudo-labels, Unbiased Teacher consistently improved state-of-the-art methods by significant margins on COCO-standard, COCO-additional, and VOC datasets. Specifically, Unbiased Teacher achieves 6.8 absolute mAP improvements against state-of-the-art method when using 1% of labeled data on MS-COCO, achieves around 10 mAP improvements against the supervised baseline when using only 0.5, 1, 2% of labeled data on MS-COCO.
Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu
tl;dr: Motivated by the self-consciousness concept in psychology, we propose a new intrinsic objective that encourages the agent to have maximum control on the environment.
Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts to remove this constraint by defining an intrinsic reward function. Motivated by the self-consciousness concept in psychology, we make a natural assumption that the agent knows what constitutes itself, and propose a new intrinsic objective that encourages the agent to have maximum control on the environment. We mathematically formalize this reward as the mutual information between the agent state and the surrounding state under the current agent policy. With this new intrinsic motivation, we are able to outperform previous methods, including being able to complete the pick-and-place task for the first time without using any task reward. A video showing experimental results is available at
Asher Trockman, J Zico Kolter
Recent work has highlighted several advantages of enforcing orthogonality in the weight layers of deep networks, such as maintaining the stability of activations, preserving gradient norms, and enhancing adversarial robustness by enforcing low Lipschitz constants. Although numerous methods exist for enforcing the orthogonality of fully-connected layers, those for convolutional layers are more heuristic in nature, often focusing on penalty methods or limited classes of convolutions. In this work, we propose and evaluate an alternative approach to directly parameterize convolutional layers that are constrained to be orthogonal. Specifically, we propose to apply the Cayley transform to a skew-symmetric convolution in the Fourier domain, so that the inverse convolution needed by the Cayley transform can be computed efficiently. We compare our method to previous Lipschitz-constrained and orthogonal convolutional layers and show that it indeed preserves orthogonality to a high degree even for large convolutions. Applied to the problem of certified adversarial robustness, we show that networks incorporating the layer outperform existing deterministic methods for certified defense against $\ell_2$-norm-bounded adversaries, while scaling to larger architectures than previously investigated. Code is available at
Bowen Jing, Stephan Eismann, Patricia Suriana, Raphael John Lamarre Townshend, Ron Dror
tl;dr: We introduce a novel graph neural network layer to learn from the structure of macromolecules.
Learning on 3D structures of large biomolecules is emerging as a distinct area in machine learning, but there has yet to emerge a unifying network architecture that simultaneously leverages the geometric and relational aspects of the problem domain. To address this gap, we introduce geometric vector perceptrons, which extend standard dense layers to operate on collections of Euclidean vectors. Graph neural networks equipped with such layers are able to perform both geometric and relational reasoning on efficient representations of macromolecules. We demonstrate our approach on two important problems in learning from protein structure: model quality assessment and computational protein design. Our approach improves over existing classes of architectures on both problems, including state-of-the-art convolutional neural networks and graph neural networks. We release our code at
Samuel L Smith, Benoit Dherin, David Barrett, Soham De
tl;dr: For small finite learning rates, the iterates of Random Shuffling SGD stay close to the path of gradient flow on a modified loss function containing an implicit regularizer.
For infinitesimal learning rates, stochastic gradient descent (SGD) follows the path of gradient flow on the full batch loss function. However moderately large learning rates can achieve higher test accuracies, and this generalization benefit is not explained by convergence bounds, since the learning rate which maximizes test accuracy is often larger than the learning rate which minimizes training loss. To interpret this phenomenon we prove that for SGD with random shuffling, the mean SGD iterate also stays close to the path of gradient flow if the learning rate is small and finite, but on a modified loss. This modified loss is composed of the original loss function and an implicit regularizer, which penalizes the norms of the minibatch gradients. Under mild assumptions, when the batch size is small the scale of the implicit regularization term is proportional to the ratio of the learning rate to the batch size. We verify empirically that explicitly including the implicit regularizer in the loss can enhance the test accuracy when the learning rate is small.
Xudong Wang, Long Lian, Zhongqi Miao, Ziwei Liu, Stella Yu
Natural data are often long-tail distributed over semantic classes. Existing recognition methods tackle this imbalanced classification by placing more emphasis on the tail data, through class re-balancing/re-weighting or ensembling over different data groups, resulting in increased tail accuracies but reduced head accuracies. We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the head-tail model bias gap remains large, due to more and larger confusion with hard negatives for the tail. We propose a new long-tailed classifier called RoutIng Diverse Experts (RIDE). It reduces the model variance with multiple experts, reduces the model bias with a distribution-aware diversity loss, reduces the computational cost with a dynamic expert routing module. RIDE outperforms the state-of-the-art by 5% to 7% on CIFAR100-LT, ImageNet-LT and iNaturalist 2018 benchmarks. It is also a universal framework that is applicable to various backbone networks, long-tailed algorithms and training mechanisms for consistent performance gains. Our code is available at:
Kashif Rasul, Abdul-Saboor Sheikh, Ingmar Schuster, Urs M Bergmann, Roland Vollgraf
tl;dr: SOTA Multivariate probabilistic time series forecasting using RNNs or Attention to model the dynamics and normalizing flows for the emission model.
Time series forecasting is often fundamental to scientific and engineering problems and enables decision making. With ever increasing data set sizes, a trivial solution to scale up predictions is to assume independence between interacting time series. However, modeling statistical dependencies can improve accuracy and enable analysis of interaction effects. Deep learning methods are well suited for this problem, but multi-variate models often assume a simple parametric distribution and do not scale to high dimensions. In this work we model the multi-variate temporal dynamics of time series via an autoregressive deep learning model, where the data distribution is represented by a conditioned normalizing flow. This combination retains the power of autoregressive models, such as good performance in extrapolation into the future, with the flexibility of flows as a general purpose high-dimensional distribution model, while remaining computationally tractable. We show that it improves over the state-of-the-art for standard metrics on many real-world data sets with several thousand interacting time-series.
Xiuyuan Cheng, Zichen Miao, Qiang Qiu
tl;dr: Graph convolution model for landmark data with local graph regularization and provable graph signal representation expressiveness and stability.
Geometric variations like rotation, scaling, and viewpoint changes pose a significant challenge to visual understanding. One common solution is to directly model certain intrinsic structures, e.g., using landmarks. However, it then becomes non-trivial to build effective deep models, especially when the underlying non-Euclidean grid is irregular and coarse. Recent deep models using graph convolutions provide an appropriate framework to handle such non-Euclidean data, but many of them, particularly those based on global graph Laplacians, lack expressiveness to capture local features required for representation of signals lying on the non-Euclidean grid. The current paper introduces a new type of graph convolution with learnable low-rank local filters, which is provably more expressive than previous spectral graph convolution methods. The model also provides a unified framework for both spectral and spatial graph convolutions. To improve model robustness, regularization by local graph Laplacians is introduced. The representation stability against input graph data perturbation is theoretically proved, making use of the graph filter locality and the local graph regularization. Experiments on spherical mesh data, real-world facial expression recognition/skeleton-based action recognition data, and data with simulated graph noise show the empirical advantage of the proposed model.
Durmus Alp Emre Acar, Yue Zhao, Ramon Matas, Matthew Mattina, Paul Whatmough, Venkatesh Saligrama
tl;dr: We present, FedDyn, a novel dynamic regularization method for Federated Learning where the risk objective for each device is dynamically updated to ensure the device optima is asymptotically consistent with stationary points of the global loss.
We propose a novel federated learning method for distributively training neural network models, where the server orchestrates cooperation between a subset of randomly chosen devices in each round. We view Federated Learning problem primarily from a communication perspective and allow more device level computations to save transmission costs. We point out a fundamental dilemma, in that the minima of the local-device level empirical loss are inconsistent with those of the global empirical loss. Different from recent prior works, that either attempt inexact minimization or utilize devices for parallelizing gradient computation, we propose a dynamic regularizer for each device at each round, so that in the limit the global and device solutions are aligned. We demonstrate both through empirical results on real and synthetic data as well as analytical results that our scheme leads to efficient training, in both convex and non-convex settings, while being fully agnostic to device heterogeneity and robust to large number of devices, partial participation and unbalanced data.
T. Konstantin Rusch, Siddhartha Mishra
tl;dr: A biologically motivated and discretized ODE based RNN for learning long-term dependencies, with rigorous bounds mitigating the exploding and vanishing gradient problem.
Circuits of biological neurons, such as in the functional parts of the brain can be modeled as networks of coupled oscillators. Inspired by the ability of these systems to express a rich set of outputs while keeping (gradients of) state variables bounded, we propose a novel architecture for recurrent neural networks. Our proposed RNN is based on a time-discretization of a system of second-order ordinary differential equations, modeling networks of controlled nonlinear oscillators. We prove precise bounds on the gradients of the hidden states, leading to the mitigation of the exploding and vanishing gradient problem for this RNN. Experiments show that the proposed RNN is comparable in performance to the state of the art on a variety of benchmarks, demonstrating the potential of this architecture to provide stable and accurate RNNs for processing complex sequential data.
Mathieu Chalvidal, Matthew Ricci, Rufin VanRullen, Thomas Serre
tl;dr: This paper presents a new method to enhance Neural ODEs representation power by dynamically controlling their weight parametrization.
Despite their elegant formulation and lightweight memory cost, neural ordinary differential equations (NODEs) suffer from known representational limitations. In particular, the single flow learned by NODEs cannot express all homeomorphisms from a given data space to itself, and their static weight parameterization restricts the type of functions they can learn compared to discrete architectures with layer-dependent weights. Here, we describe a new module called neurally-controlled ODE (N-CODE) designed to improve the expressivity of NODEs. The parameters of N-CODE modules are dynamic variables governed by a trainable map from initial or current activation state, resulting in forms of open-loop and closed-loop control, respectively. A single module is sufficient for learning a distribution on non-autonomous flows that adaptively drive neural representations. We provide theoretical and empirical evidence that N-CODE circumvents limitations of previous NODEs models and show how increased model expressivity manifests in several supervised and unsupervised learning problems. These favorable empirical results indicate the potential of using data- and activity-dependent plasticity in neural networks across numerous domains.
Da Xu, Yuting Ye, Chuanwei Ruan
tl;dr: We study the theoretical properties of importance weighting for deep learning.
The recent paper by Byrd & Lipton (2019), based on empirical observations, raises a major concern on the impact of importance weighting for the over-parameterized deep learning models. They observe that as long as the model can separate the training data, the impact of importance weighting diminishes as the training proceeds. Nevertheless, there lacks a rigorous characterization of this phenomenon. In this paper, we provide formal characterizations and theoretical justifications on the role of importance weighting with respect to the implicit bias of gradient descent and margin-based learning theory. We reveal both the optimization dynamics and generalization performance under deep learning models. Our work not only explains the various novel phenomenons observed for importance weighting in deep learning, but also extends to the studies where the weights are being optimized as part of the model, which applies to a number of topics under active research.
Yihao Feng, Ziyang Tang, na zhang, qiang liu
tl;dr: We propose an approach to constructing non-asymptotic confidence intervals of off-policy estimation.
Off-policy evaluation (OPE) is the task of estimating the expected reward of a given policy based on offline data previously collected under different policies. Therefore, OPE is a key step in applying reinforcement learning to real-world domains such as medical treatment, where interactive data collection is expensive or even unsafe. As the observed data tends to be noisy and limited, it is essential to provide rigorous uncertainty quantification, not just a point estimation, when applying OPE to make high stakes decisions. This work considers the problem of constructing non-asymptotic confidence intervals in infinite-horizon off-policy evaluation, which remains a challenging open question. We develop a practical algorithm through a primal-dual optimization-based approach, which leverages the kernel Bellman loss (KBL) of Feng et al. 2019 and a new martingale concentration inequality of KBL applicable to time-dependent data with unknown mixing conditions. Our algorithm makes minimum assumptions on the data and the function class of the Q-function, and works for the behavior-agnostic settings where the data is collected under a mix of arbitrary unknown behavior policies. We present empirical results that clearly demonstrate the advantages of our approach over existing methods.
Francesco Tonolini, Pablo Garcia Moreno, Andreas Damianou, Roderick Murray-Smith
tl;dr: Recovering accurate posterior distributions for unsupervised data recovery
We propose a new probabilistic method for unsupervised recovery of corrupted data. Given a large ensemble of degraded samples, our method recovers accurate posteriors of clean values, allowing the exploration of the manifold of possible reconstructed data and hence characterising the underlying uncertainty. In this set-ting, direct application of classical variational methods often gives rise to collapsed densities that do not adequately explore the solution space. Instead, we derive our novel reduced entropy condition approximate inference method that results in rich posteriors. We test our model in a data recovery task under the common setting of missing values and noise, demonstrating superior performance to existing variational methods for imputation and de-noising with different real data sets. We further show higher classification accuracy after imputation, proving the advantage of propagating uncertainty to downstream tasks with our model.
Cory Stephenson, suchismita padhy, Abhinav Ganesh, Yue Hui, Hanlin Tang, SueYeon Chung
tl;dr: We analyze the representational geometry of deep neural networks during generalization and memorization, and find the structure across layers of when and where memorization occurs, as well as drivers for this emerging structure.
Understanding how large neural networks avoid memorizing training data is key to explaining their high generalization performance. To examine the structure of when and where memorization occurs in a deep network, we use a recently developed replica-based mean field theoretic geometric analysis method. We find that all layers preferentially learn from examples which share features, and link this behavior to generalization performance. Memorization predominately occurs in the deeper layers, due to decreasing object manifolds’ radius and dimension, whereas early layers are minimally affected. This predicts that generalization can be restored by reverting the final few layer weights to earlier epochs before significant memorization occurred, which is confirmed by the experiments. Additionally, by studying generalization under different model sizes, we reveal the connection between the double descent phenomenon and the underlying model geometry. Finally, analytical analysis shows that networks avoid memorization early in training because close to initialization, the gradient contribution from permuted examples are small. These findings provide quantitative evidence for the structure of memorization across layers of a deep neural network, the drivers for such structure, and its connection to manifold geometric properties.
Faruk Ahmed, Yoshua Bengio, Harm van Seijen, Aaron Courville
tl;dr: Invariance penalties across splits of a biased dataset can improve systematic generalisation
We consider situations where the presence of dominant simpler correlations with the target variable in a training set can cause an SGD-trained neural network to be less reliant on more persistently correlating complex features. When the non-persistent, simpler correlations correspond to non-semantic background factors, a neural network trained on this data can exhibit dramatic failure upon encountering systematic distributional shift, where the correlating background features are recombined with different objects. We perform an empirical study on three synthetic datasets, showing that group invariance methods across inferred partitionings of the training set can lead to significant improvements at such test-time situations. We also suggest a simple invariance penalty, showing with experiments on our setups that it can perform better than alternatives. We find that even without assuming access to any systematically shifted validation sets, one can still find improvements over an ERM-trained reference model.
Stephen Tian, Suraj Nair, Frederik Ebert, Sudeep Dasari, Benjamin Eysenbach, Chelsea Finn, Sergey Levine
tl;dr: We combine model-based planning with dynamical distance learning to solve visual goal-reaching tasks, using random, unlabeled, experience.
A generalist robot must be able to complete a variety of tasks in its environment. One appealing way to specify each task is in terms of a goal observation. However, learning goal-reaching policies with reinforcement learning remains a challenging problem, particularly when hand-engineered reward functions are not available. Learned dynamics models are a promising approach for learning about the environment without rewards or task-directed data, but planning to reach goals with such a model requires a notion of functional similarity between observations and goal states. We present a self-supervised method for model-based visual goal reaching, which uses both a visual dynamics model as well as a dynamical distance function learned using model-free reinforcement learning. Our approach learns entirely using offline, unlabeled data, making it practical to scale to large and diverse datasets. In our experiments, we find that our method can successfully learn models that perform a variety of tasks at test-time, moving objects amid distractors with a simulated robotic arm and even learning to open and close a drawer using a real-world robot. In comparisons, we find that this approach substantially outperforms both model-free and model-based prior methods.
Seyed Iman Mirzadeh, Mehrdad Farajtabar, Dilan Gorur, Razvan Pascanu, Hassan Ghasemzadeh
tl;dr: We show that continual and multitask minima are connected by linear low-error paths and design an effective continual learning algorithm that exploits this property.
Continual (sequential) training and multitask (simultaneous) training are often attempting to solve the same overall objective: to find a solution that performs well on all considered tasks. The main difference is in the training regimes, where continual learning can only have access to one task at a time, which for neural networks typically leads to catastrophic forgetting. That is, the solution found for a subsequent task does not perform well on the previous ones anymore. However, the relationship between the different minima that the two training regimes arrive at is not well understood. What sets them apart? Is there a local structure that could explain the difference in performance achieved by the two different schemes? Motivated by recent work showing that different minima of the same task are typically connected by very simple curves of low error, we investigate whether multitask and continual solutions are similarly connected. We empirically find that indeed such connectivity can be reliably achieved and, more interestingly, it can be done by a linear path, conditioned on having the same initialization for both. We thoroughly analyze this observation and discuss its significance for the continual learning process. Furthermore, we exploit this finding to propose an effective algorithm that constrains the sequentially learned minima to behave as the multitask solution. We show that our method outperforms several state of the art continual learning algorithms on various vision benchmarks.
Augustus Odena, Kensen Shi, David Bieber, Rishabh Singh, Charles Sutton, Hanjun Dai
tl;dr: We use a learned model to guide a bottom-up program synthesis search to efficiently synthesize spreadsheet programs.
Program synthesis is challenging largely because of the difficulty of search in a large space of programs. Human programmers routinely tackle the task of writing complex programs by writing sub-programs and then analyzing their intermediate results to compose them in appropriate ways. Motivated by this intuition, we present a new synthesis approach that leverages learning to guide a bottom-up search over programs. In particular, we train a model to prioritize compositions of intermediate values during search conditioned on a given set of input-output examples. This is a powerful combination because of several emergent properties. First, in bottom-up search, intermediate programs can be executed, providing semantic information to the neural network. Second, given the concrete values from those executions, we can exploit rich features based on recent work on property signatures. Finally, bottom-up search allows the system substantial flexibility in what order to generate the solution, allowing the synthesizer to build up a program from multiple smaller sub-programs. Overall, our empirical evaluation finds that the combination of learning and bottom-up search is remarkably effective, even with simple supervised learning approaches. We demonstrate the effectiveness of our technique on two datasets, one from the SyGuS competition and one of our own creation.
Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, Shi Gu
We study the challenging task of neural network quantization without end-to-end retraining, called Post-training Quantization (PTQ). PTQ usually requires a small subset of training data but produces less powerful quantized models than Quantization-Aware Training (QAT). In this work, we propose a novel PTQ framework, dubbed BRECQ, which pushes the limits of bitwidth in PTQ down to INT2 for the first time. BRECQ leverages the basic building blocks in neural networks and reconstructs them one-by-one. In a comprehensive theoretical study of the second-order error, we show that BRECQ achieves a good balance between cross-layer dependency and generalization error. To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity. Extensive experiments on various handcrafted and searched neural architectures are conducted for both image classification and object detection tasks. And for the first time we prove that, without bells and whistles, PTQ can attain 4-bit ResNet and MobileNetV2 comparable with QAT and enjoy 240 times faster production of quantized models. Codes are available at
Brian Chmiel, Liad Ben-Uri, Moran Shkolnik, Elad Hoffer, Ron Banner, Daniel Soudry
While training can mostly be accelerated by reducing the time needed to propagate neural gradients (loss gradients with respect to the intermediate neural layer outputs) back throughout the model, most previous works focus on the quantization/pruning of weights and activations. These methods are often not applicable to neural gradients, which have very different statistical properties. Distinguished from weights and activations, we find that the distribution of neural gradients is approximately lognormal. Considering this, we suggest two closed-form analytical methods to reduce the computational and memory burdens of neural gradients. The first method optimizes the floating-point format and scale of the gradients. The second method accurately sets sparsity thresholds for gradient pruning. Each method achieves state-of-the-art results on ImageNet. To the best of our knowledge, this paper is the first to (1) quantize the gradients to 6-bit floating-point formats, or (2) achieve up to 85% gradient sparsity --- in each case without accuracy degradation. Reference implementation accompanies the paper in the supplementary material.
Omer Yair, Tomer Michaeli
tl;dr: We present an alternative derivation of the classical Contrastive divergence method, which reveals that it is in fact an adversarial learning procedure.
Contrastive divergence (CD) learning is a classical method for fitting unnormalized statistical models to data samples. Despite its wide-spread use, the convergence properties of this algorithm are still not well understood. The main source of difficulty is an unjustified approximation which has been used to derive the gradient of the loss. In this paper, we present an alternative derivation of CD that does not require any approximation and sheds new light on the objective that is actually being optimized by the algorithm. Specifically, we show that CD is an adversarial learning procedure, where a discriminator attempts to classify whether a Markov chain generated from the model has been time-reversed. Thus, although predating generative adversarial networks (GANs) by more than a decade, CD is, in fact, closely related to these techniques. Our derivation settles well with previous observations, which have concluded that CD's update steps cannot be expressed as the gradients of any fixed objective function. In addition, as a byproduct, our derivation reveals a simple correction that can be used as an alternative to Metropolis-Hastings rejection, which is required when the underlying Markov chain is inexact (e.g., when using Langevin dynamics with a large step).
Arda Sahiner, Tolga Ergen, John M. Pauly, Mert Pilanci
tl;dr: We demonstrate that two-layer vector-output ReLU networks can be expressed as copositive programs, and introduce algorithms for provably finding their global optima, which are polynomial in the number of samples for a fixed data rank.
We describe the convex semi-infinite dual of the two-layer vector-output ReLU neural network training problem. This semi-infinite dual admits a finite dimensional representation, but its support is over a convex set which is difficult to characterize. In particular, we demonstrate that the non-convex neural network training problem is equivalent to a finite-dimensional convex copositive program. Our work is the first to identify this strong connection between the global optima of neural networks and those of copositive programs. We thus demonstrate how neural networks implicitly attempt to solve copositive programs via semi-nonnegative matrix factorization, and draw key insights from this formulation. We describe the first algorithms for provably finding the global minimum of the vector output neural network training problem, which are polynomial in the number of samples for a fixed data rank, yet exponential in the dimension. However, in the case of convolutional architectures, the computational complexity is exponential in only the filter size and polynomial in all other parameters. We describe the circumstances in which we can find the global optimum of this neural network training problem exactly with soft-thresholded SVD, and provide a copositive relaxation which is guaranteed to be exact for certain classes of problems, and which corresponds with the solution of Stochastic Gradient Descent in practice.
Alexander Vargo, Fan Zhang, Mikhail Yurochkin, Yuekai Sun
tl;dr: We propose an algorithm for training individually fair gradient boosted decision trees classifiers.
We consider the task of enforcing individual fairness in gradient boosting. Gradient boosting is a popular method for machine learning from tabular data, which arise often in applications where algorithmic fairness is a concern. At a high level, our approach is a functional gradient descent on a (distributionally) robust loss function that encodes our intuition of algorithmic fairness for the ML task at hand. Unlike prior approaches to individual fairness that only work with smooth ML models, our approach also works with non-smooth models such as decision trees. We show that our algorithm converges globally and generalizes. We also demonstrate the efficacy of our algorithm on three ML problems susceptible to algorithmic bias.
Xingyu Cai, Jiaji Huang, Yuchen Bian, Kenneth Church
tl;dr: This paper reveals isotropy in the clustered contextual embedding space, and found low-dimensional manifolds in there.
The geometric properties of contextual embedding spaces for deep language models such as BERT and ERNIE, have attracted considerable attention in recent years. Investigations on the contextual embeddings demonstrate a strong anisotropic space such that most of the vectors fall within a narrow cone, leading to high cosine similarities. It is surprising that these LMs are as successful as they are, given that most of their embedding vectors are as similar to one another as they are. In this paper, we argue that the isotropy indeed exists in the space, from a different but more constructive perspective. We identify isolated clusters and low dimensional manifolds in the contextual embedding space, and introduce tools to both qualitatively and quantitatively analyze them. We hope the study in this paper could provide insights towards a better understanding of the deep language models.
David Widmann, Fredrik Lindsten, Dave Zachariah
tl;dr: Unifying framework for calibration evaluations and tests of probabilistic predictive models
Most supervised machine learning tasks are subject to irreducible prediction errors. Probabilistic predictive models address this limitation by providing probability distributions that represent a belief over plausible targets, rather than point estimates. Such models can be a valuable tool in decision-making under uncertainty, provided that the model output is meaningful and interpretable. Calibrated models guarantee that the probabilistic predictions are neither over- nor under-confident. In the machine learning literature, different measures and statistical tests have been proposed and studied for evaluating the calibration of classification models. For regression problems, however, research has been focused on a weaker condition of calibration based on predicted quantiles for real-valued targets. In this paper, we propose the first framework that unifies calibration evaluation and tests for general probabilistic predictive models. It applies to any such model, including classification and regression models of arbitrary dimension. Furthermore, the framework generalizes existing measures and provides a more intuitive reformulation of a recently proposed framework for calibration in multi-class classification. In particular, we reformulate and generalize the kernel calibration error, its estimators, and hypothesis tests using scalar-valued kernels, and evaluate the calibration of real-valued regression problems.
Mikhail Yurochkin, Yuekai Sun
tl;dr: We propose a new invariance-enforcing regularizer for training individually fair ML systems.
In this paper, we cast fair machine learning as invariant machine learning. We first formulate a version of individual fairness that enforces invariance on certain sensitive sets. We then design a transport-based regularizer that enforces this version of individual fairness and develop an algorithm to minimize the regularizer efficiently. Our theoretical results guarantee the proposed approach trains certifiably fair ML models. Finally, in the experimental studies we demonstrate improved fairness metrics in comparison to several recent fair training procedures on three ML tasks that are susceptible to algorithmic bias.
Ziyi Chen, Yi Zhou, Tengyu Xu, Yingbin Liang
tl;dr: This is the first work on variable convergence of proximal gradient descent-ascent algorithm for nonconvex minimax optimization under ubiquitous Kurdyka-Łojasiewicz geometry.
The gradient descent-ascent (GDA) algorithm has been widely applied to solve minimax optimization problems. In order to achieve convergent policy parameters for minimax optimization, it is important that GDA generates convergent variable sequences rather than convergent sequences of function value or gradient norm. However, the variable convergence of GDA has been proved only under convexity geometries, and it is lack of understanding in general nonconvex minimax optimization. This paper fills such a gap by studying the convergence of a more general proximal-GDA for regularized nonconvex-strongly-concave minimax optimization. Specifically, we show that proximal-GDA admits a novel Lyapunov function, which monotonically decreases in the minimax optimization process and drives the variable sequences to a critical point. By leveraging this Lyapunov function and the KL geometry that parameterizes the local geometries of general nonconvex functions, we formally establish the variable convergence of proximal-GDA to a certain critical point $x^*$, i.e., $x_t\to x^*, y_t\to y^*(x^*)$. Furthermore, over the full spectrum of the KL-parameterized geometry, we show that proximal-GDA achieves different types of convergence rates ranging from sublinear convergence up to finite-step convergence, depending on the geometry associated with the KL parameter. This is the first theoretical result on the variable convergence for nonconvex minimax optimization.
Jiaming Song, Chenlin Meng, Stefano Ermon
tl;dr: We show and justify a GAN-like iterative generative model with relatively fast sampling, high sample quality and without any adversarial training.
Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps in order to produce a sample. To accelerate sampling, we present denoising diffusion implicit models (DDIMs), a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs. In DDPMs, the generative process is defined as the reverse of a particular Markovian diffusion process. We generalize DDPMs via a class of non-Markovian diffusion processes that lead to the same training objective. These non-Markovian processes can correspond to generative processes that are deterministic, giving rise to implicit models that produce high quality samples much faster. We empirically demonstrate that DDIMs can produce high quality samples $10 \times$ to $50 \times$ faster in terms of wall-clock time compared to DDPMs, allow us to trade off computation for sample quality, perform semantically meaningful image interpolation directly in the latent space, and reconstruct observations with very low error.
Binxin Ru, Xingchen Wan, Xiaowen Dong, Michael Osborne
tl;dr: We propose a NAS method that is sample-efficient, highly performant and interpretable.
Current neural architecture search (NAS) strategies focus only on finding a single, good, architecture. They offer little insight into why a specific network is performing well, or how we should modify the architecture if we want further improvements. We propose a Bayesian optimisation (BO) approach for NAS that combines the Weisfeiler-Lehman graph kernel with a Gaussian process surrogate. Our method not only optimises the architecture in a highly data-efficient manner, but also affords interpretability by discovering useful network features and their corresponding impact on the network performance. Moreover, our method is capable of capturing the topological structures of the architectures and is scalable to large graphs, thus making the high-dimensional and graph-like search spaces amenable to BO. We demonstrate empirically that our surrogate model is capable of identifying useful motifs which can guide the generation of new architectures. We finally show that our method outperforms existing NAS approaches to achieve the state of the art on both closed- and open-domain search spaces.
Andrea Agazzi, Jianfeng Lu
tl;dr: We prove that softmax policy gradient algorithms with single hidden layer neural networks in the mean-field regime can be expressed as a gradient flow in Wasserstein space and prove that all the fixed points of such dynamics are global optimizers
We study the problem of policy optimization for infinite-horizon discounted Markov Decision Processes with softmax policy and nonlinear function approximation trained with policy gradient algorithms. We concentrate on the training dynamics in the mean-field regime, modeling e.g. the behavior of wide single hidden layer neural networks, when exploration is encouraged through entropy regularization. The dynamics of these models is established as a Wasserstein gradient flow of distributions in parameter space. We further prove global optimality of the fixed points of this dynamics under mild conditions on their initialization.
Tom Zahavy, Andre Barreto, Daniel J Mankowitz, Shaobo Hou, Brendan O'Donoghue, Iurii Kemaev, Satinder Singh
tl;dr: Discovering a set of diverse RL policies by optimising the robustness of the set
We study the problem of how to construct a set of policies that can be composed together to solve a collection of reinforcement learning tasks. Each task is a different reward function defined as a linear combination of known features. We consider a specific class of policy compositions which we call set improving policies (SIPs): given a set of policies and a set of tasks, a SIP is any composition of the former whose performance is at least as good as that of its constituents across all the tasks. We focus on the most conservative instantiation of SIPs, set-max policies (SMPs), so our analysis extends to any SIP. This includes known policy-composition operators like generalized policy improvement. Our main contribution is an algorithm that builds a set of policies in order to maximize the worst-case performance of the resulting SMP on the set of tasks. The algorithm works by successively adding new policies to the set. We show that the worst-case performance of the resulting SMP strictly improves at each iteration, and the algorithm only stops when there does not exist a policy that leads to improved performance. We empirically evaluate our algorithm on a grid world and also on a set of domains from the DeepMind control suite. We confirm our theoretical results regarding the monotonically improving performance of our algorithm. Interestingly, we also show empirically that the sets of policies computed by the algorithm are diverse, leading to different trajectories in the grid world and very distinct locomotion skills in the control suite.
Jun Han, Martin Renqiang Min, Ligong Han, Li Erran Li, Xuan Zhang
tl;dr: We propose the first recurrent Wasserstein Autoencoder for learning disentangled representations of sequential data with theoretical analysis.
Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework. However, only a few works have explored unsupervised disentangled sequential representation learning due to challenges of generating sequential data. In this paper, we propose recurrent Wasserstein Autoencoder (R-WAE), a new framework for generative modeling of sequential data. R-WAE disentangles the representation of an input sequence into static and dynamic factors (i.e., time-invariant and time-varying parts). Our theoretical analysis shows that, R-WAE minimizes an upper bound of a penalized form of the Wasserstein distance between model distribution and sequential data distribution, and simultaneously maximizes the mutual information between input data and different disentangled latent factors, respectively. This is superior to (recurrent) VAE which does not explicitly enforce mutual information maximization between input data and disentangled latent representations. When the number of actions in sequential data is available as weak supervision information, R-WAE is extended to learn a categorical latent representation of actions to improve its disentanglement. Experiments on a variety of datasets show that our models outperform other baselines with the same settings in terms of disentanglement and unconditional video generation both quantitatively and qualitatively.
Konstantinos Vougioukas, Stavros Petridis, Maja Pantic
tl;dr: A framework for domain translation which uses a novel mechanism for conditioning energy-based GANs.
Domain translation is the process of transforming data from one domain to another while preserving the common semantics. Some of the most popular domain translation systems are based on conditional generative adversarial networks, which use source domain data to drive the generator and as an input to the discriminator. However, this approach does not enforce the preservation of shared semantics since the conditional input can often be ignored by the discriminator. We propose an alternative method for conditioning and present a new framework, where two networks are simultaneously trained, in a supervised manner, to perform domain translation in opposite directions. Our method is not only better at capturing the shared information between two domains but is more generic and can be applied to a broader range of problems. The proposed framework performs well even in challenging cross-modal translations, such as video-driven speech reconstruction, for which other systems struggle to maintain correspondence.
Phil Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, Tom Goldstein
tl;dr: We measure the dimensionality of common used datasets, and experimentally investigate whether the links between dimensionality and learning that have been identified in the manifold learning literature describe the behaviors of deep neural networks.
It is widely believed that natural image data exhibits low-dimensional structure despite the high dimensionality of conventional pixel representations. This idea underlies a common intuition for the remarkable success of deep learning in computer vision. In this work, we apply dimension estimation tools to popular datasets and investigate the role of low-dimensional structure in deep learning. We find that common natural image datasets indeed have very low intrinsic dimension relative to the high number of pixels in the images. Additionally, we find that low dimensional datasets are easier for neural networks to learn, and models solving these tasks generalize better from training to test data. Along the way, we develop a technique for validating our dimension estimation tools on synthetic data generated by GANs allowing us to actively manipulate the intrinsic dimension by controlling the image generation process. Code for our experiments may be found \href{}{here}.
Christopher Frye, Damien de Mijolla, Tom Begley, Laurence Cowton, Megan Stanley, Ilya Feige
tl;dr: We present drawbacks of model explanations that do not respect the data manifold, and introduce two methods for on-manifold explainability.
Explainability in AI is crucial for model development, compliance with regulation, and providing operational nuance to predictions. The Shapley framework for explainability attributes a model’s predictions to its input features in a mathematically principled and model-agnostic way. However, general implementations of Shapley explainability make an untenable assumption: that the model’s features are uncorrelated. In this work, we demonstrate unambiguous drawbacks of this assumption and develop two solutions to Shapley explainability that respect the data manifold. One solution, based on generative modelling, provides flexible access to data imputations; the other directly learns the Shapley value-function, providing performance and stability at the cost of flexibility. While “off-manifold” Shapley values can (i) give rise to incorrect explanations, (ii) hide implicit model dependence on sensitive attributes, and (iii) lead to unintelligible explanations in higher-dimensional data, on-manifold explainability overcomes these problems.
Binh Tang, David S. Matteson
Despite significant advances, continual learning models still suffer from catastrophic forgetting when exposed to incrementally available data from non-stationary distributions. Rehearsal approaches alleviate the problem by maintaining and replaying a small episodic memory of previous samples, often implemented as an array of independent memory slots. In this work, we propose to augment such an array with a learnable random graph that captures pairwise similarities between its samples, and use it not only to learn new tasks but also to guard against forgetting. Empirical results on several benchmark datasets show that our model consistently outperforms recently proposed baselines for task-free continual learning.
Abdul Wasay, Stratos Idreos
tl;dr: We show that when we perform a holistic assessment, we uncover a wide design space, where ensembles not only provide better accuracy but also train and deploy with fewer resources than comparable single convolutional network models.
Convolutional neural networks are utilized to solve increasingly more complex problems and with more data. As a result, researchers and practitioners seek to scale the representational power of such models by adding more parameters. However, increasing parameters requires additional critical resources in terms of memory and compute, leading to increased training and inference cost. Thus a consistent challenge is to obtain as high as possible accuracy within a parameter budget. As neural network designers navigate this complex landscape, they are guided by conventional wisdom that is informed from past empirical studies. We identify a critical part of this design space that is not well-understood: How to decide between the alternatives of expanding a single convolutional network model or increasing the number of networks in the form of an ensemble. We study this question in detail across various network architectures and data sets. We build an extensive experimental framework that captures numerous angles of the possible design space in terms of how a new set of parameters can be used in a model. We consider a holistic set of metrics such as training time, inference time, and memory usage. The framework provides a robust assessment by making sure it controls for the number of parameters. Contrary to conventional wisdom, we show that when we perform a holistic and robust assessment, we uncover a wide design space, where ensembles provide better accuracy, train faster, and deploy at speed comparable to single convolutional networks with the same total number of parameters.
Dominik Schmidt, Georgia Koppe, Zahra Monfared, Max Beutelspacher, Daniel Durstewitz
tl;dr: We introduce a novel regularization for ReLU-based vanilla RNN that mitigates the exploding vs. vanishing gradient problem while retaining a simple mathematical structure that makes the RNN's dynamical systems properties partly analytically tractable
A main theoretical interest in biology and physics is to identify the nonlinear dynamical system (DS) that generated observed time series. Recurrent Neural Networks (RNN) are, in principle, powerful enough to approximate any underlying DS, but in their vanilla form suffer from the exploding vs. vanishing gradients problem. Previous attempts to alleviate this problem resulted either in more complicated, mathematically less tractable RNN architectures, or strongly limited the dynamical expressiveness of the RNN. Here we address this issue by suggesting a simple regularization scheme for vanilla RNN with ReLU activation which enables them to solve long-range dependency problems and express slow time scales, while retaining a simple mathematical structure which makes their DS properties partly analytically accessible. We prove two theorems that establish a tight connection between the regularized RNN dynamics and their gradients, illustrate on DS benchmarks that our regularization approach strongly eases the reconstruction of DS which harbor widely differing time scales, and show that our method is also en par with other long-range architectures like LSTMs on several tasks.
Huang Fang, Zhenan Fan, Michael Friedlander
This paper studies the behaviour of the stochastic subgradient descent (SSGD) method applied to over-parameterized nonsmooth optimization problems that satisfy an interpolation condition. By leveraging the composite structure of the empirical risk minimization problems, we prove that SSGD converges, respectively, with rates $O(1/\epsilon)$ and $O(\log(1/\epsilon))$ for convex and strongly-convex objectives when interpolation holds. These rates coincide with established rates for the stochastic gradient descent (SGD) method applied to smooth problems that also satisfy an interpolation condition. Our analysis provides a partial explanation for the empirical observation that sometimes SGD and SSGD behave similarly for training smooth and nonsmooth machine learning models. We also prove that the rate $O(1/\epsilon)$ is optimal for the subgradient method in the convex and interpolation setting.
Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard H Hovy
tl;dr: Generative Flow for Decoupled Representation Learning
In this work, we propose a new generative model that is capable of automatically decoupling global and local representations of images in an entirely unsupervised setting, by embedding a generative flow in the VAE framework to model the decoder. Specifically, the proposed model utilizes the variational auto-encoding framework to learn a (low-dimensional) vector of latent variables to capture the global information of an image, which is fed as a conditional input to a flow-based invertible decoder with architecture borrowed from style transfer literature. Experimental results on standard image benchmarks demonstrate the effectiveness of our model in terms of density estimation, image generation and unsupervised representation learning. Importantly, this work demonstrates that with only architectural inductive biases, a generative model with a likelihood-based objective is capable of learning decoupled representations, requiring no explicit supervision. The code for our model is available at \url{}.
Jacob Menick, Erich Elsen, Utku Evci, Simon Osindero, Karen Simonyan, Alex Graves
tl;dr: We show how to make RTRL efficient with sparse RNNs, a sparse approximation, or both.
Recurrent neural networks are usually trained with backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights "online" (after every timestep). Real Time Recurrent Learning (RTRL) eliminates the need for history storage and allows for online weight updates, but does so at the expense of computational costs that are quartic in the state size. This renders RTRL training intractable for all but the smallest networks, even ones that are made highly sparse. We introduce the Sparse n-step Approximation (SnAp) to the RTRL influence matrix. SnAp only tracks the influence of a parameter on hidden units that are reached by the computation graph within $n$ timesteps of the recurrent core. SnAp with $n=1$ is no more expensive than backpropagation but allows training on arbitrarily long sequences. We find that it substantially outperforms other RTRL approximations with comparable costs such as Unbiased Online Recurrent Optimization. For highly sparse networks, SnAp with $n=2$ remains tractable and can outperform backpropagation through time in terms of learning speed when updates are done online.
Nurit Spingarn, Ron Banner, Tomer Michaeli
tl;dr: Extracting linear & nonlinear semantic directions in GAN latent space without any required optimization
Recent research has shown remarkable success in revealing "steering" directions in the latent spaces of pre-trained GANs. These directions correspond to semantically meaningful image transformations (e.g., shift, zoom, color manipulations), and have the same interpretable effect across all categories that the GAN can generate. Some methods focus on user-specified transformations, while others discover transformations in an unsupervised manner. However, all existing techniques rely on an optimization procedure to expose those directions, and offer no control over the degree of allowed interaction between different transformations. In this paper, we show that "steering" trajectories can be computed in closed form directly from the generator's weights without any form of training or optimization. This applies to user-prescribed geometric transformations, as well as to unsupervised discovery of more complex effects. Our approach allows determining both linear and nonlinear trajectories, and has many advantages over previous methods. In particular, we can control whether one transformation is allowed to come on the expense of another (e.g., zoom-in with or without allowing translation to keep the object centered). Moreover, we can determine the natural end-point of the trajectory, which corresponds to the largest extent to which a transformation can be applied without incurring degradation. Finally, we show how transferring attributes between images can be achieved without optimization, even across different categories.
Tonghan Wang, Tarun Gupta, Anuj Mahajan, Bei Peng, Shimon Whiteson, Chongjie Zhang
tl;dr: We propose a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.
Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. However, it is largely unclear how to efficiently discover such a set of roles. To solve this problem, we propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. Learning a role selector based on action effects makes role discovery much easier because it forms a bi-level learning hierarchy: the role selector searches in a smaller role space and at a lower temporal resolution, while role policies learn in significantly reduced primitive action-observation spaces. We further integrate information about action effects into the role policies to boost learning efficiency and policy generalization. By virtue of these advances, our method (1) outperforms the current state-of-the-art MARL algorithms on 9 of the 14 scenarios that comprise the challenging StarCraft II micromanagement benchmark and (2) achieves rapid transfer to new environments with three times the number of agents. Demonstrative videos can be viewed at
Ekdeep Singh Lubana, Robert Dick
tl;dr: This paper establishes the relationship between regularly used importance measures for network pruning and evolution of model parameters under gradient flow, thus providing useful insights into pruning early-on in training.
Recent network pruning methods focus on pruning models early-on in training. To estimate the impact of removing a parameter, these methods use importance measures that were originally designed to prune trained models. Despite lacking justification for their use early-on in training, such measures result in surprisingly low accuracy loss. To better explain this behavior, we develop a general framework that uses gradient flow to unify state-of-the-art importance measures through the norm of model parameters. We use this framework to determine the relationship between pruning measures and evolution of model parameters, establishing several results related to pruning models early-on in training: (i) magnitude-based pruning removes parameters that contribute least to reduction in loss, resulting in models that converge faster than magnitude-agnostic methods; (ii) loss-preservation based pruning preserves first-order model evolution dynamics and its use is therefore justified for pruning minimally trained models; and (iii) gradient-norm based pruning affects second-order model evolution dynamics, such that increasing gradient norm via pruning can produce poorly performing models. We validate our claims on several VGG-13, MobileNet-V1, and ResNet-56 models trained on CIFAR-10/CIFAR-100.
Nadav Dym, Haggai Maron
tl;dr: We provide sufficient conditions for universality of rotation equivariant point cloud networks and use these conditions to show that current models are universal as well as for devising new universal architectures.
Learning functions on point clouds has applications in many fields, including computer vision, computer graphics, physics, and chemistry. Recently, there has been a growing interest in neural architectures that are invariant or equivariant to all three shape-preserving transformations of point clouds: translation, rotation, and permutation. In this paper, we present a first study of the approximation power of these architectures. We first derive two sufficient conditions for an equivariant architecture to have the universal approximation property, based on a novel characterization of the space of equivariant polynomials. We then use these conditions to show that two recently suggested models, Tensor field Networks and SE3-Transformers, are universal, and for devising two other novel universal architectures.
JangHyun Kim, Wonho Choo, Hosan Jeong, Hyun Oh Song
tl;dr: We propose a new perspective on joint mixup augmentation and formulate the optimal construction of a batch of mixup data.
While deep neural networks show great performance on fitting to the training distribution, improving the networks' generalization performance to the test distribution and robustness to the sensitivity to input perturbations still remain as a challenge. Although a number of mixup based augmentation strategies have been proposed to partially address them, it remains unclear as to how to best utilize the supervisory signal within each input data for mixup from the optimization perspective. We propose a new perspective on batch mixup and formulate the optimal construction of a batch of mixup data maximizing the data saliency measure of each individual mixup data and encouraging the supermodular diversity among the constructed mixup data. This leads to a novel discrete optimization problem minimizing the difference between submodular functions. We also propose an efficient modular approximation based iterative submodular minimization algorithm for efficient mixup computation per each minibatch suitable for minibatch based neural network training. Our experiments show the proposed method achieves the state of the art generalization, calibration, and weakly supervised localization results compared to other mixup methods. The source code is available at
Yuliang Zou, Zizhao Zhang, Han Zhang, Chun-Liang Li, Xiao Bian, Jia-Bin Huang, Tomas Pfister
tl;dr: This paper presents a new method that first demonstrates how well-calibrated soft pseudo labels obtained through wise fusion of predictions from diverse sources greatly improve consistency training for semantic segmentation.
Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification, semantic segmentation tasks require much more intensive labeling costs. Thus, these tasks greatly benefit from data-efficient training methods. However, structured outputs in segmentation render particular difficulties (e.g., designing pseudo-labeling and augmentation) to apply existing SSL strategies. To address this problem, we present a simple and novel re-design of pseudo-labeling to generate well-calibrated structured pseudo labels for training with unlabeled or weakly-labeled data. Our proposed pseudo-labeling strategy is network structure agnostic to apply in a one-stage consistency training framework. We demonstrate the effectiveness of the proposed pseudo-labeling strategy in both low-data and high-data regimes. Extensive experiments have validated that pseudo labels generated from wisely fusing diverse sources and strong data augmentation are crucial to consistency training for segmentation. The source code will be released.
Ekin Akyürek, Afra Feyza Akyürek, Jacob Andreas
tl;dr: This paper investigates a data augmentation procedure based on two weaker principles: recombination and resampling, and finds that it is sufficient to induce many of the compositional generalizations studied in previous work.
Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training data—particularly to rare or unseen subsequences. Past work has found symbolic scaffolding (e.g. grammars or automata) essential in these settings. We describe R&R, a learned data augmentation scheme that enables a large category of compositional generalizations without appeal to latent symbolic structure. R&R has two components: recombination of original training examples via a prototype-based generative model and resampling of generated examples to encourage extrapolation. Training an ordinary neural sequence model on a dataset augmented with recombined and resampled examples significantly improves generalization in two language processing problems—instruction following (SCAN) and morphological analysis (SIGMORPHON 2018)—where R&R enables learning of new constructions and tenses from as few as eight initial examples.
Aymeric Fromherz, Klas Leino, Matt Fredrikson, Bryan Parno, Corina Pasareanu
tl;dr: We present a fast, scalable procedure for checking local robustness in neural networks
Local robustness ensures that a model classifies all inputs within an $\ell_p$-ball consistently, which precludes various forms of adversarial inputs. In this paper, we present a fast procedure for checking local robustness in feed-forward neural networks with piecewise-linear activation functions. Such networks partition the input space into a set of convex polyhedral regions in which the network’s behavior is linear; hence, a systematic search for decision boundaries within the regions around a given input is sufficient for assessing robustness. Crucially, we show how the regions around a point can be analyzed using simple geometric projections, thus admitting an efficient, highly-parallel GPU implementation that excels particularly for the $\ell_2$ norm, where previous work has been less effective. Empirically we find this approach to be far more precise than many approximate verification approaches, while at the same time performing multiple orders of magnitude faster than complete verifiers, and scaling to much deeper networks.
Binghong Chen, Tianzhe Wang, Chengtao Li, Hanjun Dai, Le Song
tl;dr: We propose a novel EM-like evolution-by-explanation algorithm alternating between an explainable graph model and a conditional generative model for molecule optimization.
Optimizing molecules for desired properties is a fundamental yet challenging task in chemistry, material science, and drug discovery. This paper develops a novel algorithm for optimizing molecular properties via an Expectation-Maximization (EM) like explainable evolutionary process. The algorithm is designed to mimic human experts in the process of searching for desirable molecules and alternate between two stages: the first stage on explainable local search which identifies rationales, i.e., critical subgraph patterns accounting for desired molecular properties, and the second stage on molecule completion which explores the larger space of molecules containing good rationales. We test our approach against various baselines on a real-world multi-property optimization task where each method is given the same number of queries to the property oracle. We show that our evolution-by-explanation algorithm is 79% better than the best baseline in terms of a generic metric combining aspects such as success rate, novelty, and diversity. Human expert evaluation on optimized molecules shows that 60% of top molecules obtained from our methods are deemed successful.
Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou
tl;dr: A theoretical point of view for Mixup training
Mixup is a popular data augmentation technique based on on convex combinations of pairs of examples and their labels. This simple technique has shown to substantially improve both the model's robustness as well as the generalization of the trained model. However, it is not well-understood why such improvement occurs. In this paper, we provide theoretical analysis to demonstrate how using Mixup in training helps model robustness and generalization. For robustness, we show that minimizing the Mixup loss corresponds to approximately minimizing an upper bound of the adversarial loss. This explains why models obtained by Mixup training exhibits robustness to several kinds of adversarial attacks such as Fast Gradient Sign Method (FGSM). For generalization, we prove that Mixup augmentation corresponds to a specific type of data-adaptive regularization which reduces overfitting. Our analysis provides new insights and a framework to understand Mixup.
Kangle Deng, Aayush Bansal, Deva Ramanan
tl;dr: We present an unsupervised approach that converts the input speech of any individual into audiovisual streams of potentially-infinitely many output speakers.
We present an unsupervised approach that converts the input speech of any individual into audiovisual streams of potentially-infinitely many output speakers. Our approach builds on simple autoencoders that project out-of-sample data onto the distribution of the training set. We use exemplar autoencoders to learn the voice, stylistic prosody, and visual appearance of a specific target exemplar speech. In contrast to existing methods, the proposed approach can be easily extended to an arbitrarily large number of speakers and styles using only 3 minutes of target audio-video data, without requiring any training data for the input speaker. To do so, we learn audiovisual bottleneck representations that capture the structured linguistic content of speech. We outperform prior approaches on both audio and video synthesis.
Shangqing Liu, Yu Chen, Xiaofei Xie, Jing Kai Siow, Yang Liu
tl;dr: This paper proposes a novel retrieval-augmented mechanism to augment the code semantics with hybrid graph neural network for source code summarization.
Source code summarization aims to generate natural language summaries from structured code snippets for better understanding code functionalities. However, automatic code summarization is challenging due to the complexity of the source code and the language gap between the source code and natural language summaries. Most previous approaches either rely on retrieval-based (which can take advantage of similar examples seen from the retrieval database, but have low generalization performance) or generation-based methods (which have better generalization performance, but cannot take advantage of similar examples). This paper proposes a novel retrieval-augmented mechanism to combine the benefits of both worlds. Furthermore, to mitigate the limitation of Graph Neural Networks (GNNs) on capturing global graph structure information of source code, we propose a novel attention-based dynamic graph to complement the static graph representation of the source code, and design a hybrid message passing GNN for capturing both the local and global structural information. To evaluate the proposed approach, we release a new challenging benchmark, crawled from diversified large-scale open-source C projects (total 95k+ unique functions in the dataset). Our method achieves the state-of-the-art performance, improving existing methods by 1.42, 2.44 and 1.29 in terms of BLEU-4, ROUGE-L and METEOR.
Xinshuai Dong, Anh Tuan Luu, Rongrong Ji, Hong Liu
tl;dr: Capture adversarial word substitutions in the vector space using convex hull towards robustness.
Robustness against word substitutions has a well-defined and widely acceptable form, i.e., using semantically similar words as substitutions, and thus it is considered as a fundamental stepping-stone towards broader robustness in natural language processing. Previous defense methods capture word substitutions in vector space by using either l_2-ball or hyper-rectangle, which results in perturbation sets that are not inclusive enough or unnecessarily large, and thus impedes mimicry of worst cases for robust training. In this paper, we introduce a novel Adversarial Sparse Convex Combination (ASCC) method. We model the word substitution attack space as a convex hull and leverages a regularization term to enforce perturbation towards an actual substitution, thus aligning our modeling better with the discrete textual space. Based on ASCC method, we further propose ASCC-defense, which leverages ASCC to generate worst-case perturbations and incorporates adversarial training towards robustness. Experiments show that ASCC-defense outperforms the current state-of-the-arts in terms of robustness on two prevailing NLP tasks, i.e., sentiment analysis and natural language inference, concerning several attacks across multiple model architectures. Besides, we also envision a new class of defense towards robustness in NLP, where our robustly trained word vectors can be plugged into a normally trained model and enforce its robustness without applying any other defense techniques.
Alexander Norcliffe, Cristian Bodnar, Ben Day, Jacob Moss, Pietro Liò
tl;dr: Neural Processes with time-awareness
Neural Ordinary Differential Equations (NODEs) use a neural network to model the instantaneous rate of change in the state of a system. However, despite their apparent suitability for dynamics-governed time-series, NODEs present a few disadvantages. First, they are unable to adapt to incoming data-points, a fundamental requirement for real-time applications imposed by the natural direction of time. Second, time-series are often composed of a sparse set of measurements that could be explained by many possible underlying dynamics. NODEs do not capture this uncertainty. In contrast, Neural Processes (NPs) are a new class of stochastic processes providing uncertainty estimation and fast data-adaptation, but lack an explicit treatment of the flow of time. To address these problems, we introduce Neural ODE Processes (NDPs), a new class of stochastic processes determined by a distribution over Neural ODEs. By maintaining an adaptive data-dependent distribution over the underlying ODE, we show that our model can successfully capture the dynamics of low-dimensional systems from just a few data-points. At the same time, we demonstrate that NDPs scale up to challenging high-dimensional time-series with unknown latent dynamics such as rotating MNIST digits.
Liam Li, Mikhail Khodak, Nina Balcan, Ameet Talwalkar
tl;dr: Studying the right single-level optimization geometry yields state-of-the-art methods for NAS.
Recent state-of-the-art methods for neural architecture search (NAS) exploit gradient-based optimization by relaxing the problem into continuous optimization over architectures and shared-weights, a noisy process that remains poorly understood. We argue for the study of single-level empirical risk minimization to understand NAS with weight-sharing, reducing the design of NAS methods to devising optimizers and regularizers that can quickly obtain high-quality solutions to this problem. Invoking the theory of mirror descent, we present a geometry-aware framework that exploits the underlying structure of this optimization to return sparse architectural parameters, leading to simple yet novel algorithms that enjoy fast convergence guarantees and achieve state-of-the-art accuracy on the latest NAS benchmarks in computer vision. Notably, we exceed the best published results for both CIFAR and ImageNet on both the DARTS search space and NAS-Bench-201; on the latter we achieve near-oracle-optimal performance on CIFAR-10 and CIFAR-100. Together, our theory and experiments demonstrate a principled way to co-design optimizers and continuous relaxations of discrete NAS search spaces.
Ishaan Gulrajani, David Lopez-Paz
tl;dr: Our ERM baseline achieves state-of-the-art performance across many domain generalization benchmarks
The goal of domain generalization algorithms is to predict well on distributions different from those seen during training. While a myriad of domain generalization algorithms exist, inconsistencies in experimental conditions---datasets, network architectures, and model selection criteria---render fair comparisons difficult. The goal of this paper is to understand how useful domain generalization algorithms are in realistic settings. As a first step, we realize that model selection is non-trivial for domain generalization tasks, and we argue that algorithms without a model selection criterion remain incomplete. Next we implement DomainBed, a testbed for domain generalization including seven benchmarks, fourteen algorithms, and three model selection criteria. When conducting extensive experiments using DomainBed we find that when carefully implemented and tuned, ERM outperforms the state-of-the-art in terms of average performance. Furthermore, no algorithm included in DomainBed outperforms ERM by more than one point when evaluated under the same experimental conditions. We hope that the release of DomainBed, alongside contributions from fellow researchers, will streamline reproducible and rigorous advances in domain generalization.
Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Kraehenbuehl
tl;dr: MONeT reduces the memory footprint of training while minimizing compute overhead by jointly optimizing checkpointing with operator optimizations.
Deep learning is slowly, but steadily, hitting a memory bottleneck. While the tensor computation in top-of-the-line GPUs increased by $32\times$ over the last five years, the total available memory only grew by $2.5\times$. This prevents researchers from exploring larger architectures, as training large networks requires more memory for storing intermediate outputs. In this paper, we present MONeT, an automatic framework that minimizes both the memory footprint and computational overhead of deep networks. MONeT jointly optimizes the checkpointing schedule and the implementation of various operators. MONeT is able to outperform all prior hand-tuned operations as well as automated checkpointing. MONeT reduces the overall memory requirement by $3\times$ for various PyTorch models, with a 9-16$\%$ overhead in computation. For the same computation cost, MONeT requires 1.2-1.8$\times$ less memory than current state-of-the-art automated checkpointing frameworks. Our code will be made publicly available upon acceptance.
Dongsu Zhang, Changwoon Choi, Jeonghwan Kim, Young Min Kim
tl;dr: We present a Markov chain based 3D generative model named Generative Cellular Automata (GCA), that progressively evolves to a shape of the learned distribution using the local update rules of cellular automata.
In this work, we present a probabilistic 3D generative model, named Generative Cellular Automata, which is able to produce diverse and high quality shapes. We formulate the shape generation process as sampling from the transition kernel of a Markov chain, where the sampling chain eventually evolves to the full shape of the learned distribution. The transition kernel employs the local update rules of cellular automata, effectively reducing the search space in a high-resolution 3D grid space by exploiting the connectivity and sparsity of 3D shapes. Our progressive generation only focuses on the sparse set of occupied voxels and their neighborhood, thus enables the utilization of an expressive sparse convolutional network. We propose an effective training scheme to obtain the local homogeneous rule of generative cellular automata with sequences that are slightly different from the sampling chain but converge to the full shapes in the training data. Extensive experiments on probabilistic shape completion and shape generation demonstrate that our method achieves competitive performance against recent methods.
Like Hui, Mikhail Belkin
tl;dr: An experimental evaluation of neural architectures in classification tasks shows that training with square loss produces better results than the cross-entropy in the majority of NLP and ASR experiments.
Modern neural architectures for classification tasks are trained using the cross-entropy loss, which is widely believed to be empirically superior to the square loss. In this work we provide evidence indicating that this belief may not be well-founded. We explore several major neural architectures and a range of standard benchmark datasets for NLP, automatic speech recognition (ASR) and computer vision tasks to show that these architectures, with the same hyper-parameter settings as reported in the literature, perform comparably or better when trained with the square loss, even after equalizing computational resources. Indeed, we observe that the square loss produces better results in the dominant majority of NLP and ASR experiments. Cross-entropy appears to have a slight edge on computer vision tasks. We argue that there is little compelling empirical or theoretical evidence indicating a clear-cut advantage to the cross-entropy loss. Indeed, in our experiments, performance on nearly all non-vision tasks can be improved, sometimes significantly, by switching to the square loss. Furthermore, training with square loss appears to be less sensitive to the randomness in initialization. We posit that training using the square loss for classification needs to be a part of best practices of modern deep learning on equal footing with cross-entropy.
Huan Wang, Can Qin, Yulun Zhang, Yun Fu
tl;dr: We propose two new deep network pruning algorithms based a growing regularization paradigm.
Regularization has long been utilized to learn sparsity in deep neural network pruning. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new scenario where the regularization grows large gradually to tackle two central problems of pruning: pruning schedule and weight importance scoring. (1) The former topic is newly brought up in this work, which we find critical to the pruning performance while receives little research attention. Specifically, we propose an L2 regularization variant with rising penalty factors and show it can bring significant accuracy gains compared with its one-shot counterpart, even when the same weights are removed. (2) The growing penalty scheme also brings us an approach to exploit the Hessian information for more accurate pruning without knowing their specific values, thus not bothered by the common Hessian approximation problems. Empirically, the proposed algorithms are easy to implement and scalable to large datasets and networks in both structured and unstructured pruning. Their effectiveness is demonstrated with modern deep neural networks on the CIFAR and ImageNet datasets, achieving competitive results compared to many state-of-the-art algorithms. Our code and trained models are publicly available at
Alberto Bietti, Francis Bach
Deep networks are often considered to be more expressive than shallow ones in terms of approximation. Indeed, certain functions can be approximated by deep networks provably more efficiently than by shallow ones, however, no tractable algorithms are known for learning such deep models. Separately, a recent line of work has shown that deep networks trained with gradient descent may behave like (tractable) kernel methods in a certain over-parameterized regime, where the kernel is determined by the architecture and initialization, and this paper focuses on approximation for such kernels. We show that for ReLU activations, the kernels derived from deep fully-connected networks have essentially the same approximation properties as their shallow two-layer counterpart, namely the same eigenvalue decay for the corresponding integral operator. This highlights the limitations of the kernel framework for understanding the benefits of such deep architectures. Our main theoretical result relies on characterizing such eigenvalue decays through differentiability properties of the kernel function, which also easily applies to the study of other kernels defined on the sphere.
Denis Yarats, Ilya Kostrikov, Rob Fergus
tl;dr: The first successful demonstration that image augmentation can be applied to image-based Deep RL to achieve SOTA performance.
We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach leverages input perturbations commonly used in computer vision tasks to transform input examples, as well as regularizing the value function and policy. Existing model-free approaches, such as Soft Actor-Critic (SAC), are not able to train deep networks effectively from image pixels. However, the addition of our augmentation method dramatically improves SAC’s performance, enabling it to reach state-of-the-art performance on the DeepMind control suite, surpassing model-based (Hafner et al., 2019; Lee et al., 2019; Hafner et al., 2018) methods and recently proposed contrastive learning (Srinivas et al., 2020). Our approach, which we dub DrQ: Data-regularized Q, can be combined with any model-free reinforcement learning algorithm. We further demonstrate this by applying it to DQN and significantly improve its data-efficiency on the Atari 100k benchmark.
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby
tl;dr: Transformers applied directly to image patches and pre-trained on large datasets work really well on image classification.
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.
Ryohei Shimizu, YUSUKE Mukuta, Tatsuya Harada
tl;dr: We present novel methods for constructing hyperbolic neural network architectures in the Poincaré ball model, including a parameter-reduced MLR, geodesic-aware FC layers, convolutional layers, and attention mechanisms.
Hyperbolic spaces, which have the capacity to embed tree structures without distortion owing to their exponential volume growth, have recently been applied to machine learning to better capture the hierarchical nature of data. In this study, we generalize the fundamental components of neural networks in a single hyperbolic geometry model, namely, the Poincaré ball model. This novel methodology constructs a multinomial logistic regression, fully-connected layers, convolutional layers, and attention mechanisms under a unified mathematical interpretation, without increasing the parameters. Experiments show the superior parameter efficiency of our methods compared to conventional hyperbolic components, and stability and outperformance over their Euclidean counterparts.
Max Smith, Thomas Anthony, Michael Wellman
tl;dr: On each epoch, train against a single opponent policy rather than a distribution; reducing variance and focusing training on salient strategic knowledge.
Policy-Space Response Oracles (PSRO) is a general algorithmic framework for learning policies in multiagent systems by interleaving empirical game analysis with deep reinforcement learning (DRL). At each iteration, DRL is invoked to train a best response to a mixture of opponent policies. The repeated application of DRL poses an expensive computational burden as we look to apply this algorithm to more complex domains. We introduce two variations of PSRO designed to reduce the amount of simulation required during DRL training. Both algorithms modify how PSRO adds new policies to the empirical game, based on learned responses to a single opponent policy. The first, Mixed-Oracles, transfers knowledge from previous iterations of DRL, requiring training only against the opponent's newest policy. The second, Mixed-Opponents, constructs a pure-strategy opponent by mixing existing strategy's action-value estimates, instead of their policies. Learning against a single policy mitigates conflicting experiences on behalf of a learner facing an unobserved distribution of opponents. We empirically demonstrate that these algorithms substantially reduce the amount of simulation during training required by PSRO, while producing equivalent or better solutions to the game.
Mary Phuong, Christoph H Lampert
tl;dr: We characterise the function learnt by two-layer ReLU nets trained on orthogonally separable data.
We study the inductive bias of two-layer ReLU networks trained by gradient flow. We identify a class of easy-to-learn (`orthogonally separable') datasets, and characterise the solution that ReLU networks trained on such datasets converge to. Irrespective of network width, the solution turns out to be a combination of two max-margin classifiers: one corresponding to the positive data subset and one corresponding to the negative data subset. The proof is based on the recently introduced concept of extremal sectors, for which we prove a number of properties in the context of orthogonal separability. In particular, we prove stationarity of activation patterns from some time $T$ onwards, which enables a reduction of the ReLU network to an ensemble of linear subnetworks.
J. Krishna Murthy, Miles Macklin, Florian Golemo, Vikram Voleti, Linda Petrini, Martin Weiss, Breandan Considine, Jérôme Parent-Lévesque, Kevin Xie, Kenny Erleben, Liam Paull, Florian Shkurti, Derek Nowrouzezahrai, Sanja Fidler
tl;dr: Differentiable models of time-varying dynamics and image formation pipelines result in highly accurate physical parameter estimation from video
In this paper, we tackle the problem of estimating object physical properties such as mass, friction, and elasticity directly from video sequences. Such a system identification problem is fundamentally ill-posed due to the loss of information during image formation. Current best solutions to the problem require precise 3D labels which are labor intensive to gather, and infeasible to create for many systems such as deformable solids or cloth. In this work we present gradSim, a framework that overcomes the dependence on 3D supervision by combining differentiable multiphysics simulation and differentiable rendering to jointly model the evolution of scene dynamics and image formation. This unique combination enables backpropagation from pixels in a video sequence through to the underlying physical attributes that generated them. Furthermore, our unified computation graph across dynamics and rendering engines enables the learning of challenging visuomotor control tasks, without relying on state-based (3D) supervision, while obtaining performance competitive to/better than techniques that require precise 3D labels.
Shivangi Mahto, Vy Ai Vo, Javier S. Turek, Alexander Huth
tl;dr: This work presents a theoretically-motivated analysis of memory and timescale in LSTM language models.
Language models must capture statistical dependencies between words at timescales ranging from very short to very long. Earlier work has demonstrated that dependencies in natural language tend to decay with distance between words according to a power law. However, it is unclear how this knowledge can be used for analyzing or designing neural network language models. In this work, we derived a theory for how the memory gating mechanism in long short-term memory (LSTM) language models can capture power law decay. We found that unit timescales within an LSTM, which are determined by the forget gate bias, should follow an Inverse Gamma distribution. Experiments then showed that LSTM language models trained on natural English text learn to approximate this theoretical distribution. Further, we found that explicitly imposing the theoretical distribution upon the model during training yielded better language model perplexity overall, with particular improvements for predicting low-frequency (rare) words. Moreover, the explicit multi-timescale model selectively routes information about different types of words through units with different timescales, potentially improving model interpretability. These results demonstrate the importance of careful, theoretically-motivated analysis of memory and timescale in language models.
Fumihiro Sasaki, Ryota Yamashina
tl;dr: We propose an imitation learning algorithm to learn from non-optimal (noisy) demonstrations without any environment interactions and annotations associated with the demonstrations.
We consider the problem of learning an optimal expert behavior policy given noisy demonstrations that contain observations from both optimal and non-optimal expert behaviors. Popular imitation learning algorithms, such as generative adversarial imitation learning, assume that (clear) demonstrations are given from optimal expert policies but not the non-optimal ones, and thus often fail to imitate the optimal expert behaviors given the noisy demonstrations. Prior works that address the problem require (1) learning policies through environment interactions in the same fashion as reinforcement learning, and (2) annotating each demonstration with confidence scores or rankings. However, such environment interactions and annotations in real-world settings take impractically long training time and a significant human effort. In this paper, we propose an imitation learning algorithm to address the problem without any environment interactions and annotations associated with the non-optimal demonstrations. The proposed algorithm learns ensemble policies with a generalized behavioral cloning (BC) objective function where we exploit another policy already learned by BC. Experimental results show that the proposed algorithm can learn behavior policies that are much closer to the optimal policies than ones learned by BC.
Yu Tian, Jian Ren, Menglei Chai, Kyle Olszewski, Xi Peng, Dimitris N. Metaxas, Sergey Tulyakov
tl;dr: Reuse a pre-trained image generator for high-resolution video synthesis
Image and video synthesis are closely related areas aiming at generating content from noise. While rapid progress has been demonstrated in improving image-based models to handle large resolutions, high-quality renderings, and wide variations in image content, achieving comparable video generation results remains problematic. We present a framework that leverages contemporary image generators to render high-resolution videos. We frame the video synthesis problem as discovering a trajectory in the latent space of a pre-trained and fixed image generator. Not only does such a framework render high-resolution videos, but it also is an order of magnitude more computationally efficient. We introduce a motion generator that discovers the desired trajectory, in which content and motion are disentangled. With such a representation, our framework allows for a broad range of applications, including content and motion manipulation. Furthermore, we introduce a new task, which we call cross-domain video synthesis, in which the image and motion generators are trained on disjoint datasets belonging to different domains. This allows for generating moving objects for which the desired video data is not available. Extensive experiments on various datasets demonstrate the advantages of our methods over existing video generation techniques. Code will be released at
Kartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, Richard Hartley
tl;dr: We introduce a binning-free calibration measure inspired by the classical Kolmogorov-Smirnov statistical test and obtain a recalibration function by approximating the empirical cumulative distribution using a differentiable function via splines.
Calibrating neural networks is of utmost importance when employing them in safety-critical applications where the downstream decision making depends on the predicted probabilities. Measuring calibration error amounts to comparing two empirical distributions. In this work, we introduce a binning-free calibration measure inspired by the classical Kolmogorov-Smirnov (KS) statistical test in which the main idea is to compare the respective cumulative probability distributions. From this, by approximating the empirical cumulative distribution using a differentiable function via splines, we obtain a recalibration function, which maps the network outputs to actual (calibrated) class assignment probabilities. The spline-fitting is performed using a held-out calibration set and the obtained recalibration function is evaluated on an unseen test set. We tested our method against existing calibration approaches on various image classification datasets and our spline-based recalibration approach consistently outperforms existing methods on KS error as well as other commonly used calibration measures. Code is available online at
Bingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed Elgammal
tl;dr: A computational-efficient GAN for few-shot hi-fi image dataset (converge on single gpu with few hours' training, on 1024 resolution sub-hundred images).
Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for GAN with minimum computing cost. We propose a light-weight GAN structure that gains superior quality on 1024^2 resolution. Notably, the model converges from scratch with just a few hours of training on a single RTX-2080 GPU, and has a consistent performance, even with less than 100 training samples. Two technique designs constitute our work, a skip-layer channel-wise excitation module and a self-supervised discriminator trained as a feature-encoder. With thirteen datasets covering a wide variety of image domains (The datasets and code are available at, we show our model's superior performance compared to the state-of-the-art StyleGAN2, when data and computing budget are limited.
Benjamin David Haeffele, Chong You, Rene Vidal
tl;dr: Here we show theoretically and experimentally that there are a number of flaws with many existing self-expressive deep subspace clustering models.
Subspace clustering is an unsupervised clustering technique designed to cluster data that is supported on a union of linear subspaces, with each subspace defining a cluster with dimension lower than the ambient space. Many existing formulations for this problem are based on exploiting the self-expressive property of linear subspaces, where any point within a subspace can be represented as linear combination of other points within the subspace. To extend this approach to data supported on a union of non-linear manifolds, numerous studies have proposed learning an embedding of the original data using a neural network which is regularized by a self-expressive loss function on the data in the embedded space to encourage a union of linear subspaces prior on the data in the embedded space. Here we show that there are a number of potential flaws with this approach which have not been adequately addressed in prior work. In particular, we show the model formulation is often ill-posed in that it can lead to a degenerate embedding of the data, which need not correspond to a union of subspaces at all and is poorly suited for clustering. We validate our theoretical results experimentally and also repeat prior experiments reported in the literature, where we conclude that a significant portion of the previously claimed performance benefits can be attributed to an ad-hoc post processing step rather than the deep subspace clustering model.
Zhisheng Xiao, Karsten Kreis, Jan Kautz, Arash Vahdat
tl;dr: We introduce an energy-based generative model where the data distribution is defined jointly by a VAE and an energy network.
Energy-based models (EBMs) have recently been successful in representing complex distributions of small images. However, sampling from them requires expensive Markov chain Monte Carlo (MCMC) iterations that mix slowly in high dimensional pixel space. Unlike EBMs, variational autoencoders (VAEs) generate samples quickly and are equipped with a latent space that enables fast traversal of the data manifold. However, VAEs tend to assign high probability density to regions in data space outside the actual data distribution and often fail at generating sharp images. In this paper, we propose VAEBM, a symbiotic composition of a VAE and an EBM that offers the best of both worlds. VAEBM captures the overall mode structure of the data distribution using a state-of-the-art VAE and it relies on its EBM component to explicitly exclude non-data-like regions from the model and refine the image samples. Moreover, the VAE component in VAEBM allows us to speed up MCMC updates by reparameterizing them in the VAE's latent space. Our experimental results show that VAEBM outperforms state-of-the-art VAEs and EBMs in generative quality on several benchmark image datasets by a large margin. It can generate high-quality images as large as 256$\times$256 pixels with short MCMC chains. We also demonstrate that VAEBM provides complete mode coverage and performs well in out-of-distribution detection.
Laurence Aitchison
tl;dr: We develop a generative model of dataset curation that explains the cold-posterior effect
To get Bayesian neural networks to perform comparably to standard neural networks it is usually necessary to artificially reduce uncertainty using a tempered or cold posterior. This is extremely concerning: if the prior is accurate, Bayes inference/decision theory is optimal, and any artificial changes to the posterior should harm performance. While this suggests that the prior may be at fault, here we argue that in fact, BNNs for image classification use the wrong likelihood. In particular, standard image benchmark datasets such as CIFAR-10 are carefully curated. We develop a generative model describing curation which gives a principled Bayesian account of cold posteriors, because the likelihood under this new generative model closely matches the tempered likelihoods used in past work.
Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip Torr
tl;dr: Interpolating label noise hurts adversarial robustness
We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models. When trained with SGD, deep neural networks essentially achieve zero training error, even in the presence of label noise, while also exhibiting good generalization on natural test data, something referred to as benign overfitting (Bartlett et al., 2020; Chatterji & Long, 2020). However, these models are vulnerable to adversarial attacks. We identify label noise as one of the causes for adversarial vulnerability, and provide theoretical and empirical evidence in support of this. Surprisingly, we find several instances of label noise in datasets such as MNIST and CIFAR, and that robustly trained models incur training error on some of these, i.e. they don’t fit the noise. However, removing noisy labels alone does not suffice to achieve adversarial robustness. We conjecture that in part sub-optimal representation learning is also responsible for adversarial vulnerability. By means of simple theoretical setups, we show how the choice of representation can drastically affect adversarial robustness.
Nils Wandel, Michael Weinmann, Reinhard Klein
tl;dr: We present an unsupervised training framework for incompressible fluid dynamics that allows neural networks to perform fast, accurate, differentiable fluid simulations and generalize to new domain geometries.
Fast and stable fluid simulations are an essential prerequisite for applications ranging from computer-generated imagery to computer-aided design in research and development. However, solving the partial differential equations of incompressible fluids is a challenging task and traditional numerical approximation schemes come at high computational costs. Recent deep learning based approaches promise vast speed-ups but do not generalize to new fluid domains, require fluid simulation data for training, or rely on complex pipelines that outsource major parts of the fluid simulation to traditional methods. In this work, we propose a novel physics-constrained training approach that generalizes to new fluid domains, requires no fluid simulation data, and allows convolutional neural networks to map a fluid state from time-point t to a subsequent state at time t+dt in a single forward pass. This simplifies the pipeline to train and evaluate neural fluid models. After training, the framework yields models that are capable of fast fluid simulations and can handle various fluid phenomena including the Magnus effect and Kármán vortex streets. We present an interactive real-time demo to show the speed and generalization capabilities of our trained models. Moreover, the trained neural networks are efficient differentiable fluid solvers as they offer a differentiable update step to advance the fluid simulation in time. We exploit this fact in a proof-of-concept optimal control experiment. Our models significantly outperform a recent differentiable fluid solver in terms of computational speed and accuracy.
Ankit Vani, Max Schwarzer, Yuchen Lu, Eeshan Dhekane, Aaron Courville
tl;dr: We use iterated learning to encourage the emergence of structure in the generated programs for neural module networks.
Although neural module networks have an architectural bias towards compositionality, they require gold standard layouts to generalize systematically in practice. When instead learning layouts and modules jointly, compositionality does not arise automatically and an explicit pressure is necessary for the emergence of layouts exhibiting the right structure. We propose to address this problem using iterated learning, a cognitive science theory of the emergence of compositional languages in nature that has primarily been applied to simple referential games in machine learning. Considering the layouts of module networks as samples from an emergent language, we use iterated learning to encourage the development of structure within this language. We show that the resulting layouts support systematic generalization in neural agents solving the more complex task of visual question-answering. Our regularized iterated learning method can outperform baselines without iterated learning on SHAPES-SyGeT (SHAPES Systematic Generalization Test), a new split of the SHAPES dataset we introduce to evaluate systematic generalization, and on CLOSURE, an extension of CLEVR also designed to test systematic generalization. We demonstrate superior performance in recovering ground-truth compositional program structure with limited supervision on both SHAPES-SyGeT and CLEVR.
Leon Lang, Maurice Weiler
tl;dr: We parameterize equivariant convolution kernels by proving a generalization of the Wigner-Eckart theorem for spherical tensor operators.
Group equivariant convolutional networks (GCNNs) endow classical convolutional networks with additional symmetry priors, which can lead to a considerably improved performance. Recent advances in the theoretical description of GCNNs revealed that such models can generally be understood as performing convolutions with $G$-steerable kernels, that is, kernels that satisfy an equivariance constraint themselves. While the $G$-steerability constraint has been derived, it has to date only been solved for specific use cases - a general characterization of $G$-steerable kernel spaces is still missing. This work provides such a characterization for the practically relevant case of $G$ being any compact group. Our investigation is motivated by a striking analogy between the constraints underlying steerable kernels on the one hand and spherical tensor operators from quantum mechanics on the other hand. By generalizing the famous Wigner-Eckart theorem for spherical tensor operators, we prove that steerable kernel spaces are fully understood and parameterized in terms of 1) generalized reduced matrix elements, 2) Clebsch-Gordan coefficients, and 3) harmonic basis functions on homogeneous spaces.
Chaithanya Kumar Mummadi, Ranjitha Subramaniam, Robin Hutmacher, Julien Vitay, Volker Fischer, Jan Hendrik Metzen
tl;dr: We show that robustness on common corruptions donot correlate with strong shape bias but with the effective data augmentation strategies like stylization
Convolutional neural networks (CNNs) learn to extract representations of complex features, such as object shapes and textures to solve image recognition tasks. Recent work indicates that CNNs trained on ImageNet are biased towards features that encode textures and that these alone are sufficient to generalize to unseen test data from the same distribution as the training data but often fail to generalize to out-of-distribution data. It has been shown that augmenting the training data with different image styles decreases this texture bias in favor of increased shape bias while at the same time improving robustness to common corruptions, such as noise and blur. Commonly, this is interpreted as shape bias increasing corruption robustness. However, this relationship is only hypothesized. We perform a systematic study of different ways of composing inputs based on natural images, explicit edge information, and stylization. While stylization is essential for achieving high corruption robustness, we do not find a clear correlation between shape bias and robustness. We conclude that the data augmentation caused by style-variation accounts for the improved corruption robustness and increased shape bias is only a byproduct.
Xiaorui Liu, Yao Li, Rongrong Wang, Jiliang Tang, Ming Yan
tl;dr: A Linear Convergent Decentralized Optimization with Communication Compression
Communication compression has become a key strategy to speed up distributed optimization. However, existing decentralized algorithms with compression mainly focus on compressing DGD-type algorithms. They are unsatisfactory in terms of convergence rate, stability, and the capability to handle heterogeneous data. Motivated by primal-dual algorithms, this paper proposes the first \underline{L}in\underline{EA}r convergent \underline{D}ecentralized algorithm with compression, LEAD. Our theory describes the coupled dynamics of the inexact primal and dual update as well as compression error, and we provide the first consensus error bound in such settings without assuming bounded gradients. Experiments on convex problems validate our theoretical analysis, and empirical study on deep neural nets shows that LEAD is applicable to non-convex problems.
Dmitry Krotov, John J. Hopfield
tl;dr: Our paper proposes a microscopic biologically-plausible theory of modern Hopfield networks.
Dense Associative Memories or modern Hopfield networks permit storage and reliable retrieval of an exponentially large (in the dimension of feature space) number of memories. At the same time, their naive implementation is non-biological, since it seemingly requires the existence of many-body synaptic junctions between the neurons. We show that these models are effective descriptions of a more microscopic (written in terms of biological degrees of freedom) theory that has additional (hidden) neurons and only requires two-body interactions between them. For this reason our proposed microscopic theory is a valid model of large associative memory with a degree of biological plausibility. The dynamics of our network and its reduced dimensional equivalent both minimize energy (Lyapunov) functions. When certain dynamical variables (hidden neurons) are integrated out from our microscopic theory, one can recover many of the models that were previously discussed in the literature, e.g. the model presented in "Hopfield Networks is All You Need" paper. We also provide an alternative derivation of the energy function and the update rule proposed in the aforementioned paper and clarify the relationships between various models of this class.
Adam Gleave, Michael D Dennis, Shane Legg, Stuart Russell, Jan Leike
tl;dr: A theoretically principled distance measure on reward functions that is quick to compute and predicts policy training performance.
For many tasks, the reward function is inaccessible to introspection or too complex to be specified procedurally, and must instead be learned from user data. Prior work has evaluated learned reward functions by evaluating policies optimized for the learned reward. However, this method cannot distinguish between the learned reward function failing to reflect user preferences and the policy optimization process failing to optimize the learned reward. Moreover, this method can only tell us about behavior in the evaluation environment, but the reward may incentivize very different behavior in even a slightly different deployment environment. To address these problems, we introduce the Equivalent-Policy Invariant Comparison (EPIC) distance to quantify the difference between two reward functions directly, without a policy optimization step. We prove EPIC is invariant on an equivalence class of reward functions that always induce the same optimal policy. Furthermore, we find EPIC can be efficiently approximated and is more robust than baselines to the choice of coverage distribution. Finally, we show that EPIC distance bounds the regret of optimal policies even under different transition dynamics, and we confirm empirically that it predicts policy training success. Our source code is available at
Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin
tl;dr: We propose Cyclic Precision Training towards better accuracy-efficiency trade-offs in DNN training.
Low-precision deep neural network (DNN) training has gained tremendous attention as reducing precision is one of the most effective knobs for boosting DNNs' training time/energy efficiency. In this paper, we attempt to explore low-precision training from a new perspective as inspired by recent findings in understanding DNN training: we conjecture that DNNs' precision might have a similar effect as the learning rate during DNN training, and advocate dynamic precision along the training trajectory for further boosting the time/energy efficiency of DNN training. Specifically, we propose Cyclic Precision Training (CPT) to cyclically vary the precision between two boundary values which can be identified using a simple precision range test within the first few training epochs. Extensive simulations and ablation studies on five datasets and eleven models demonstrate that CPT's effectiveness is consistent across various models/tasks (including classification and language modeling). Furthermore, through experiments and visualization we show that CPT helps to (1) converge to a wider minima with a lower generalization error and (2) reduce training variance which we believe opens up a new design knob for simultaneously improving the optimization and efficiency of DNN training.
Jaehoon Oh, Hyungjun Yoo, ChangHwan Kim, Se-Young Yun
tl;dr: We propose a novel meta-learning algorithm, BOIL, based on representation change.
Model Agnostic Meta-Learning (MAML) is one of the most representative of gradient-based meta-learning algorithms. MAML learns new tasks with a few data samples using inner updates from a meta-initialization point and learns the meta-initialization parameters with outer updates. It has recently been hypothesized that representation reuse, which makes little change in efficient representations, is the dominant factor in the performance of the meta-initialized model through MAML in contrast to representation change, which causes a significant change in representations. In this study, we investigate the necessity of representation change for the ultimate goal of few-shot learning, which is solving domain-agnostic tasks. To this aim, we propose a novel meta-learning algorithm, called BOIL (Body Only update in Inner Loop), which updates only the body (extractor) of the model and freezes the head (classifier) during inner loop updates. BOIL leverages representation change rather than representation reuse. A frozen head cannot achieve better results than even a random guessing classifier at the initial point of new tasks, and feature vectors (representations) have to move quickly to their corresponding frozen head vectors. We visualize this property using cosine similarity, CKA, and empirical results without the head. Although the inner loop updates purely hinge on representation change, BOIL empirically shows significant performance improvement over MAML, particularly on cross-domain tasks. The results imply that representation change in gradient-based meta-learning approaches is a critical component.
Charles Lovering, Rohan Jha, Tal Linzen, Ellie Pavlick
tl;dr: We find that feature extractability, measured by probing classifiers, can be viewed as an inductive bias: the more extractable a feature is after pre-training, the less statistical evidence needed during fine-tuning for the model to use the feature.
Most current NLP systems are based on a pre-train-then-fine-tune paradigm, in which a large neural network is first trained in a self-supervised way designed to encourage the network to extract broadly-useful linguistic features, and then fine-tuned for a specific task of interest. Recent work attempts to understand why this recipe works and explain when it fails. Currently, such analyses have produced two sets of apparently-contradictory results. Work that analyzes the representations that result from pre-training (via "probing classifiers") finds evidence that rich features of linguistic structure can be decoded with high accuracy, but work that analyzes model behavior after fine-tuning (via "challenge sets") indicates that decisions are often not based on such structure but rather on spurious heuristics specific to the training set. In this work, we test the hypothesis that the extent to which a feature influences a model's decisions can be predicted using a combination of two factors: The feature's "extractability" after pre-training (measured using information-theoretic probing techniques), and the "evidence" available during fine-tuning (defined as the feature's co-occurrence rate with the label). In experiments with both synthetic and natural language data, we find strong evidence (statistically significant correlations) supporting this hypothesis.
Shuo Yang, Lu Liu, Min Xu
tl;dr: The code is available at:
Learning from a limited number of samples is challenging since the learned model can easily become overfitted based on the biased distribution formed by only a few training examples. In this paper, we calibrate the distribution of these few-sample classes by transferring statistics from the classes with sufficient examples. Then an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier. We assume every dimension in the feature representation follows a Gaussian distribution so that the mean and the variance of the distribution can borrow from that of similar classes whose statistics are better estimated with an adequate number of samples. Our method can be built on top of off-the-shelf pretrained feature extractors and classification models without extra parameters. We show that a simple logistic regression classifier trained using the features sampled from our calibrated distribution can outperform the state-of-the-art accuracy on three datasets (~5% improvement on miniImageNet compared to the next best). The visualization of these generated features demonstrates that our calibrated distribution is an accurate estimation.
Elan Sopher Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Sami Abu-El-Haija, Bryan Perozzi, Greg Ver Steeg, Aram Galstyan
tl;dr: GTTF is a meta-algorithm, upon which, many algorithms for graph learning can be implemented, automatically giving them efficiency and scale, yet unbiased learning.
Graph Representation Learning (GRL) methods have impacted fields from chemistry to social science. However, their algorithmic implementations are specialized to specific use-cases e.g. "message passing" methods are run differently from "node embedding" ones. Despite their apparent differences, all these methods utilize the graph structure, and therefore, their learning can be approximated with stochastic graph traversals. We propose Graph Traversal via Tensor Functionals (GTTF), a unifying meta-algorithm framework for easing the implementation of diverse graph algorithms and enabling transparent and efficient scaling to large graphs. GTTF is founded upon a data structure (stored as a sparse tensor) and a stochastic graph traversal algorithm (described using tensor operations). The algorithm is a functional that accept two functions, and can be specialized to obtain a variety of GRL models and objectives, simply by changing those two functions. We show for a wide class of methods, our algorithm learns in an unbiased fashion and, in expectation, approximates the learning as if the specialized implementations were run directly. With these capabilities, we scale otherwise non-scalable methods to set state-of-the-art on large graph datasets while being more efficient than existing GRL libraries -- with only a handful of lines of code for each method specialization.
Wenda Li, Lei Yu, Yuhuai Wu, Lawrence C. Paulson
tl;dr: We present a benchmark for high-level mathematical reasoning and study the reasoning capabilities of neural sequence-to-sequence models.
A well-defined benchmark is essential for measuring and accelerating research progress of machine learning models. In this paper, we present a benchmark for high-level mathematical reasoning and study the reasoning capabilities of neural sequence-to-sequence models. We build a non-synthetic dataset from the largest repository of proofs written by human experts in a theorem prover. The dataset has a broad coverage of undergraduate and research-level mathematical and computer science theorems. In our defined task, a model is required to fill in a missing intermediate proposition given surrounding proofs. This task provides a starting point for the long-term goal of having machines generate human-readable proofs automatically. Our experiments and analysis reveal that while the task is challenging, neural models can capture non-trivial mathematical reasoning. We further design a hierarchical transformer that outperforms the transformer baseline.
He Zhao, Dinh Phung, Viet Huynh, Trung Le, Wray Buntine
tl;dr: This paper presents a neural topic model via optimal transport, which can discover more coherent and diverse topics and derive better document representations for both regular and short texts.
Recently, Neural Topic Models (NTMs) inspired by variational autoencoders have obtained increasingly research interest due to their promising results on text analysis. However, it is usually hard for existing NTMs to achieve good document representation and coherent/diverse topics at the same time. Moreover, they often degrade their performance severely on short documents. The requirement of reparameterisation could also comprise their training quality and model flexibility. To address these shortcomings, we present a new neural topic model via the theory of optimal transport (OT). Specifically, we propose to learn the topic distribution of a document by directly minimising its OT distance to the document's word distributions. Importantly, the cost matrix of the OT distance models the weights between topics and words, which is constructed by the distances between topics and words in an embedding space. Our proposed model can be trained efficiently with a differentiable loss. Extensive experiments show that our framework significantly outperforms the state-of-the-art NTMs on discovering more coherent and diverse topics and deriving better document representations for both regular and short texts.
Hao Peng, Nikolaos Pappas, Dani Yogatama, Roy Schwartz, Noah Smith, Lingpeng Kong
tl;dr: We propose a random-feature-based attention that scales linearly in sequence length, and performs on par with strong transformer baselines on language modeling and machine translation.
Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not scale efficiently to long sequences due to its quadratic time and space complexity in the sequence length. We propose RFA, a linear time and space attention that uses random feature methods to approximate the softmax function, and explore its application in transformers. RFA can be used as a drop-in replacement for conventional softmax attention and offers a straightforward way of learning with recency bias through an optional gating mechanism. Experiments on language modeling and machine translation demonstrate that RFA achieves similar or better performance compared to strong transformer baselines. In the machine translation experiment, RFA decodes twice as fast as a vanilla transformer. Compared to existing efficient transformer variants, RFA is competitive in terms of both accuracy and efficiency on three long text classification datasets. Our analysis shows that RFA’s efficiency gains are especially notable on long sequences, suggesting that RFA will be particularly useful in tasks that require working with large inputs, fast decoding speed, or low memory footprints.
Patrick Kidger, Terry Lyons
tl;dr: Differentiable, GPU-capable implementations of the (log)signature transform via novel algorithms.
Signatory is a library for calculating and performing functionality related to the signature and logsignature transforms. The focus is on machine learning, and as such includes features such as CPU parallelism, GPU support, and backpropagation. To our knowledge it is the first GPU-capable library for these operations. Signatory implements new features not available in previous libraries, such as efficient precomputation strategies. Furthermore, several novel algorithmic improvements are introduced, producing substantial real-world speedups even on the CPU without parallelism. The library operates as a Python wrapper around C++, and is compatible with the PyTorch ecosystem. It may be installed directly via \texttt{pip}. Source code, documentation, examples, benchmarks and tests may be found at \texttt{\url{}}. The license is Apache-2.0.
Nicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Alenyà, Pieter Abbeel, Alexei A Efros, Lerrel Pinto, Xiaolong Wang
tl;dr: Generalization across enviroments is known to be hard. We propose a self-supervised method for policy adaptation during deployment that assumes no prior knowledge of the test environment, yet still obtains significant improvements.
In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments is known to be hard. A natural solution would be to keep training after deployment in the new environment, but this cannot be done if the new environment offers no reward signal. Our work explores the use of self-supervision to allow the policy to continue training after deployment without using any rewards. While previous methods explicitly anticipate changes in the new environment, we assume no prior knowledge of those changes yet still obtain significant improvements. Empirical evaluations are performed on diverse simulation environments from DeepMind Control suite and ViZDoom, as well as real robotic manipulation tasks in continuously changing environments, taking observations from an uncalibrated camera. Our method improves generalization in 31 out of 36 environments across various tasks and outperforms domain randomization on a majority of environments. Webpage and implementation:
Stanislav Morozov, Andrey Voynov, Artem Babenko
tl;dr: We show that the state-of-the-art self-supervised representations should be used when comparing GANs on the non-Imagenet datasets
The embeddings from CNNs pretrained on Imagenet classification are de-facto standard image representations for assessing GANs via FID, Precision and Recall measures. Despite broad previous criticism of their usage for non-Imagenet domains, these embeddings are still the top choice in most of the GAN literature. In this paper, we advocate the usage of the state-of-the-art self-supervised representations to evaluate GANs on the established non-Imagenet benchmarks. These representations, typically obtained via contrastive learning, are shown to provide better transfer to new tasks and domains, therefore, can serve as more universal embeddings of natural images. With extensive comparison of the recent GANs on the common datasets, we show that self-supervised representations produce a more reasonable ranking of models in terms of FID/Precision/Recall, while the ranking with classification-pretrained embeddings often can be misleading.
Freya Behrens, Jonathan Sauder, Peter Jung
tl;dr: We introduce Neurally Augmented ALISTA, extending ALISTA to compute adaptive parameters to achieve improved recovery of individual sparse target vectors.
It is well-established that many iterative sparse reconstruction algorithms can be unrolled to yield a learnable neural network for improved empirical performance. A prime example is learned ISTA (LISTA) where weights, step sizes and thresholds are learned from training data. Recently, Analytic LISTA (ALISTA) has been introduced, combining the strong empirical performance of a fully learned approach like LISTA, while retaining theoretical guarantees of classical compressed sensing algorithms and significantly reducing the number of parameters to learn. However, these parameters are trained to work in expectation, often leading to suboptimal reconstruction of individual targets. In this work we therefore introduce Neurally Augmented ALISTA, in which an LSTM network is used to compute step sizes and thresholds individually for each target vector during reconstruction. This adaptive approach is theoretically motivated by revisiting the recovery guarantees of ALISTA. We show that our approach further improves empirical performance in sparse reconstruction, in particular outperforming existing algorithms by an increasing margin as the compression ratio becomes more challenging.
Markus Norman Rabe, Dennis Lee, Kshitij Bansal, Christian Szegedy
tl;dr: We demonstrate that self-supervised language modeling applied to mathematical formulas enables logical reasoning.
We demonstrate that self-supervised language modeling applied to mathematical formulas enables logical reasoning. To measure the logical reasoning abilities of language models, we formulate several evaluation (downstream) tasks, such as inferring types, suggesting missing assumptions and completing equalities. For training language models for formal mathematics, we propose a novel skip-tree task. We find that models trained on the skip-tree task show surprisingly strong mathematical reasoning abilities, and outperform models trained on standard skip-sequence tasks. We also analyze the models' ability to formulate new conjectures by measuring how often the predictions are provable and useful in other proofs.
Muhammet Balcilar, Guillaume Renton, Pierre Héroux, Benoit Gaüzère, Sébastien Adam, Paul Honeine
tl;dr: This paper aims to analyse of the expressive power of Graph Neural Network in spectral domain.
In the recent literature of Graph Neural Networks (GNN), the expressive power of models has been studied through their capability to distinguish if two given graphs are isomorphic or not. Since the graph isomorphism problem is NP-intermediate, and Weisfeiler-Lehman (WL) test can give sufficient but not enough evidence in polynomial time, the theoretical power of GNNs is usually evaluated by the equivalence of WL-test order, followed by an empirical analysis of the models on some reference inductive and transductive datasets. However, such analysis does not account the signal processing pipeline, whose capability is generally evaluated in the spectral domain. In this paper, we argue that a spectral analysis of GNNs behavior can provide a complementary point of view to go one step further in the understanding of GNNs. By bridging the gap between the spectral and spatial design of graph convolutions, we theoretically demonstrate some equivalence of the graph convolution process regardless it is designed in the spatial or the spectral domain. Using this connection, we managed to re-formulate most of the state-of-the-art graph neural networks into one common framework. This general framework allows to lead a spectral analysis of the most popular GNNs, explaining their performance and showing their limits according to spectral point of view. Our theoretical spectral analysis is confirmed by experiments on various graph databases. Furthermore, we demonstrate the necessity of high and/or band-pass filters on a graph dataset, while the majority of GNN is limited to only low-pass and inevitably it fails.
Shun-ichi Amari, Jimmy Ba, Roger Baker Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu
tl;dr: Characterized the generalization error of preconditioned least squares regression in the overparameterized regime and determined the optimal preconditioner.
While second order optimizers such as natural gradient descent (NGD) often speed up optimization, their effect on generalization has been called into question. This work presents a more nuanced view on how the \textit{implicit bias} of optimizers affects the comparison of generalization properties. We provide an exact asymptotic bias-variance decomposition of the generalization error of preconditioned ridgeless regression in the overparameterized regime, and consider the inverse population Fisher information matrix (used in NGD) as a particular example. We determine the optimal preconditioner $\boldsymbol{P}$ for both the bias and variance, and find that the relative generalization performance of different optimizers depends on label noise and ``shape'' of the signal (true parameters): when the labels are noisy, the model is misspecified, or the signal is misaligned with the features, NGD can achieve lower risk; conversely, GD generalizes better under clean labels, a well-specified model, or aligned signal. Based on this analysis, we discuss several approaches to manage the bias-variance tradeoff, and the potential benefit of interpolating between first- and second-order updates. We then extend our analysis to regression in the reproducing kernel Hilbert space and demonstrate that preconditioning can lead to more efficient decrease in the population risk. Lastly, we empirically compare the generalization error of first- and second-order optimizers in neural network experiments, and observe robust trends matching our theoretical analysis.
Yangchen Pan, Kirby Banman, Martha White
tl;dr: A simple and efficient way to learn sparse feature online in deep learning setting.
Recent work has shown that sparse representations---where only a small percentage of units are active---can significantly reduce interference. Those works, however, relied on relatively complex regularization or meta-learning approaches, that have only been used offline in a pre-training phase. In this work, we pursue a direction that achieves sparsity by design, rather than by learning. Specifically, we design an activation function that produces sparse representations deterministically by construction, and so is more amenable to online training. The idea relies on the simple approach of binning, but overcomes the two key limitations of binning: zero gradients for the flat regions almost everywhere, and lost precision---reduced discrimination---due to coarse aggregation. We introduce a Fuzzy Tiling Activation (FTA) that provides non-negligible gradients and produces overlap between bins that improves discrimination. We first show that FTA is robust under covariate shift in a synthetic online supervised learning problem, where we can vary the level of correlation and drift. Then we move to the deep reinforcement learning setting and investigate both value-based and policy gradient algorithms that use neural networks with FTAs, in classic discrete control and Mujoco continuous control environments. We show that algorithms equipped with FTAs are able to learn a stable policy faster without needing target networks on most domains.
Divyansh Kaushik, Amrith Setlur, Eduard H Hovy, Zachary Chase Lipton
tl;dr: We present a framework for thinking about counterfactually augmented data and make strides towards understanding its benefits in out-of-domain generalization.
In attempts to produce machine learning models less reliant on spurious patterns in NLP datasets, researchers have recently proposed curating counterfactually augmented data (CAD) via a human-in-the-loop process in which given some documents and their (initial) labels, humans must revise the text to make a counterfactual label applicable. Importantly, edits that are not necessary to flip the applicable label are prohibited. Models trained on the augmented (original and revised) data appear, empirically, to rely less on semantically irrelevant words and to generalize better out of domain. While this work draws loosely on causal thinking, the underlying causal model (even at an abstract level) and the principles underlying the observed out-of-domain improvements remain unclear. In this paper, we introduce a toy analog based on linear Gaussian models, observing interesting relationships between causal models, measurement noise, out-of-domain generalization, and reliance on spurious signals. Our analysis provides some insights that help to explain the efficacy of CAD. Moreover, we develop the hypothesis that while adding noise to causal features should degrade both in-domain and out-of-domain performance, adding noise to non-causal features should lead to relative improvements in out-of-domain performance. This idea inspires a speculative test for determining whether a feature attribution technique has identified the causal spans. If adding noise (e.g., by random word flips) to the highlighted spans degrades both in-domain and out-of-domain performance on a battery of challenge datasets, but adding noise to the complement gives improvements out-of-domain, this suggests we have identified causal spans. Thus, we present a large scale empirical study comparing spans edited to create CAD to those selected by attention and saliency maps. Across numerous challenge domains and models, we find that the hypothesized phenomenon is pronounced for CAD.
Yuchen Liang, Chaitanya Ryali, Benjamin Hoover, Leopold Grinberg, Saket Navlakha, Mohammed J Zaki, Dmitry Krotov
tl;dr: We show that a network motif from the fruit fly brain can learn word embeddings.
The mushroom body of the fruit fly brain is one of the best studied systems in neuroscience. At its core it consists of a population of Kenyon cells, which receive inputs from multiple sensory modalities. These cells are inhibited by the anterior paired lateral neuron, thus creating a sparse high dimensional representation of the inputs. In this work we study a mathematical formalization of this network motif and apply it to learning the correlational structure between words and their context in a corpus of unstructured text, a common natural language processing (NLP) task. We show that this network can learn semantic representations of words and can generate both static and context-dependent word embeddings. Unlike conventional methods (e.g., BERT, GloVe) that use dense representations for word embedding, our algorithm encodes semantic meaning of words and their context in the form of sparse binary hash codes. The quality of the learned representations is evaluated on word similarity analysis, word-sense disambiguation, and document classification. It is shown that not only can the fruit fly network motif achieve performance comparable to existing methods in NLP, but, additionally, it uses only a fraction of the computational resources (shorter training time and smaller memory footprint).
Anastasios Nikolas Angelopoulos, Stephen Bates, Michael Jordan, Jitendra Malik
tl;dr: We quantify uncertainty for image classifiers using prediction sets, with detailed experiments on Imagenet Val and V2.
Convolutional image classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, hindering their deployment in consequential settings. Existing uncertainty quantification techniques, such as Platt scaling, attempt to calibrate the network’s probability estimates, but they do not have formal guarantees. We present an algorithm that modifies any classifier to output a predictive set containing the true label with a user-specified probability, such as 90%. The algorithm is simple and fast like Platt scaling, but provides a formal finite-sample coverage guarantee for every model and dataset. Our method modifies an existing conformal prediction algorithm to give more stable predictive sets by regularizing the small scores of unlikely classes after Platt scaling. In experiments on both Imagenet and Imagenet-V2 with ResNet-152 and other classifiers, our scheme outperforms existing approaches, achieving coverage with sets that are often factors of 5 to 10 smaller than a stand-alone Platt scaling baseline.
Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang
tl;dr: We propose the Nasty Teacher, a defensive approach to prevent unauthorized cloning from a teacher model through knowledge distillation.
Knowledge Distillation (KD) is a widely used technique to transfer knowledge from pre-trained teacher models to (usually more lightweight) student models. However, in certain situations, this technique is more of a curse than a blessing. For instance, KD poses a potential risk of exposing intellectual properties (IPs): even if a trained machine learning model is released in ``black boxes'' (e.g., as executable software or APIs without open-sourcing code), it can still be replicated by KD through imitating input-output behaviors. To prevent this unwanted effect of KD, this paper introduces and investigates a concept called $\textit{Nasty Teacher}$: a specially trained teacher network that yields nearly the same performance as a normal one, but would significantly degrade the performance of student models learned by imitating it. We propose a simple yet effective algorithm to build the nasty teacher, called $\textit{self-undermining knowledge distillation}$. Specifically, we aim to maximize the difference between the output of the nasty teacher and a normal pre-trained network. Extensive experiments on several datasets demonstrate that our method is effective on both standard KD and data-free KD, providing the desirable KD-immunity to model owners for the first time. We hope our preliminary study can draw more awareness and interest in this new practical problem of both social and legal importance. Our codes and pre-trained models can be found at: $\url{}$.
Jungo Kasai, Nikolaos Pappas, Hao Peng, James Cross, Noah Smith
tl;dr: We show that the speed disadvantage for autoregressive baselines to evaluate non-autoregressive machine translation is overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation.
Much recent effort has been invested in non-autoregressive neural machine translation, which appears to be an efficient alternative to state-of-the-art autoregressive machine translation on modern GPUs. In contrast to the latter, where generation is sequential, the former allows generation to be parallelized across target token positions. Some of the latest non-autoregressive models have achieved impressive translation quality-speed tradeoffs compared to autoregressive baselines. In this work, we reexamine this tradeoff and argue that autoregressive baselines can be substantially sped up without loss in accuracy. Specifically, we study autoregressive models with encoders and decoders of varied depths. Our extensive experiments show that given a sufficiently deep encoder, a single-layer autoregressive decoder can substantially outperform strong non-autoregressive models with comparable inference speed. We show that the speed disadvantage for autoregressive baselines compared to non-autoregressive methods has been overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation. Our results establish a new protocol for future research toward fast, accurate machine translation. Our code is available at
Kangkang Lu, Cuong Manh Nguyen, Xun Xu, Kiran Chari, Yu Jing Goh, Chuan-Sheng Foo
tl;dr: ARMOURED is a novel technique for adversarially robust learning that elegantly unifies semi-supervised learning and diversity regularization through a multi-view learning framework.
Adversarial attacks pose a major challenge for modern deep neural networks. Recent advancements show that adversarially robust generalization requires a large amount of labeled data for training. If annotation becomes a burden, can unlabeled data help bridge the gap? In this paper, we propose ARMOURED, an adversarially robust training method based on semi-supervised learning that consists of two components. The first component applies multi-view learning to simultaneously optimize multiple independent networks and utilizes unlabeled data to enforce labeling consistency. The second component reduces adversarial transferability among the networks via diversity regularizers inspired by determinantal point processes and entropy maximization. Experimental results show that under small perturbation budgets, ARMOURED is robust against strong adaptive adversaries. Notably, ARMOURED does not rely on generating adversarial samples during training. When used in combination with adversarial training, ARMOURED yields competitive performance with the state-of-the-art adversarially-robust benchmarks on SVHN and outperforms them on CIFAR-10, while offering higher clean accuracy.
Yunhao Ge, Sami Abu-El-Haija, Gan Xin, Laurent Itti
tl;dr: To aid neural networks to envision objects with different attributes, we propose GSL which allows us to decompose inputs into a disentangled representation with swappable components, that can be recombined to synthesize new samples.
Visual cognition of primates is superior to that of artificial neural networks in its ability to “envision” a visual object, even a newly-introduced one, in different attributes including pose, position, color, texture, etc. To aid neural networks to envision objects with different attributes, we propose a family of objective functions, expressed on groups of examples, as a novel learning framework that we term Group-Supervised Learning (GSL). GSL allows us to decompose inputs into a disentangled representation with swappable components, that can be recombined to synthesize new samples. For instance, images of red boats & blue cars can be decomposed and recombined to synthesize novel images of red cars. We propose an implementation based on auto-encoder, termed group-supervised zero-shot synthesis network (GZS-Net) trained with our learning framework, that can produce a high-quality red car even if no such example is witnessed during training. We test our model and learning framework on existing benchmarks, in addition to a new dataset that we open-source. We qualitatively and quantitatively demonstrate that GZS-Net trained with GSL outperforms state-of-the-art methods
Zuyue Fu, Zhuoran Yang, Zhaoran Wang
We study the global convergence and global optimality of actor-critic, one of the most popular families of reinforcement learning algorithms. While most existing works on actor-critic employ bi-level or two-timescale updates, we focus on the more practical single-timescale setting, where the actor and critic are updated simultaneously. Specifically, in each iteration, the critic update is obtained by applying the Bellman evaluation operator only once while the actor is updated in the policy gradient direction computed using the critic. Moreover, we consider two function approximation settings where both the actor and critic are represented by linear or deep neural networks. For both cases, we prove that the actor sequence converges to a globally optimal policy at a sublinear $O(K^{-1/2})$ rate, where $K$ is the number of iterations. To the best of our knowledge, we establish the rate of convergence and global optimality of single-timescale actor-critic with linear function approximation for the first time. Moreover, under the broader scope of policy optimization with nonlinear function approximation, we prove that actor-critic with deep neural network finds the globally optimal policy at a sublinear rate for the first time.
Marcel Neunhoeffer, Steven Wu, Cynthia Dwork
Differentially private GANs have proven to be a promising approach for generating realistic synthetic data without compromising the privacy of individuals. Due to the privacy-protective noise introduced in the training, the convergence of GANs becomes even more elusive, which often leads to poor utility in the output generator at the end of training. We propose Private post-GAN boosting (Private PGB), a differentially private method that combines samples produced by the sequence of generators obtained during GAN training to create a high-quality synthetic dataset. To that end, our method leverages the Private Multiplicative Weights method (Hardt and Rothblum, 2010) to reweight generated samples. We evaluate Private PGB on two dimensional toy data, MNIST images, US Census data and a standard machine learning prediction task. Our experiments show that Private PGB improves upon a standard private GAN approach across a collection of quality measures. We also provide a non-private variant of PGB that improves the data quality of standard GAN training.
Pratyush Maini, Mohammad Yaghini, Nicolas Papernot
tl;dr: We introduce 'Dataset Inference' as a new method towards resolving model ownership.
With increasingly more data and computation involved in their training, machine learning models constitute valuable intellectual property. This has spurred interest in model stealing, which is made more practical by advances in learning with partial, little, or no supervision. Existing defenses focus on inserting unique watermarks in a model's decision surface, but this is insufficient: the watermarks are not sampled from the training distribution and thus are not always preserved during model stealing. In this paper, we make the key observation that knowledge contained in the stolen model's training set is what is common to all stolen copies. The adversary's goal, irrespective of the attack employed, is always to extract this knowledge or its by-products. This gives the original model's owner a strong advantage over the adversary: model owners have access to the original training data. We thus introduce $\textit{dataset inference}$, the process of identifying whether a suspected model copy has private knowledge from the original model's dataset, as a defense against model stealing. We develop an approach for dataset inference that combines statistical testing with the ability to estimate the distance of multiple data points to the decision boundary. Our experiments on CIFAR10, SVHN, CIFAR100 and ImageNet show that model owners can claim with confidence greater than 99% that their model (or dataset as a matter of fact) was stolen, despite only exposing 50 of the stolen model's training points. Dataset inference defends against state-of-the-art attacks even when the adversary is adaptive. Unlike prior work, it does not require retraining or overfitting the defended model.
Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, Xiao Wang
tl;dr: A method that enables parties to improve their own local heterogeneous machine learning models in a collaborative setting where both confidentiality and privacy need to be preserved to prevent both explicit and implicit sharing of private data.
Machine learning benefits from large training datasets, which may not always be possible to collect by any single entity, especially when using privacy-sensitive data. In many contexts, such as healthcare and finance, separate parties may wish to collaborate and learn from each other's data but are prevented from doing so due to privacy regulations. Some regulations prevent explicit sharing of data between parties by joining datasets in a central location (confidentiality). Others also limit implicit sharing of data, e.g., through model predictions (privacy). There is currently no method that enables machine learning in such a setting, where both confidentiality and privacy need to be preserved, to prevent both explicit and implicit sharing of data. Federated learning only provides confidentiality, not privacy, since gradients shared still contain private information. Differentially private learning assumes unreasonably large datasets. Furthermore, both of these learning paradigms produce a central model whose architecture was previously agreed upon by all parties rather than enabling collaborative learning where each party learns and improves their own local model. We introduce Confidential and Private Collaborative (CaPC) learning, the first method provably achieving both confidentiality and privacy in a collaborative setting. We leverage secure multi-party computation (MPC), homomorphic encryption (HE), and other techniques in combination with privately aggregated teacher models. We demonstrate how CaPC allows participants to collaborate without having to explicitly join their training sets or train a central model. Each party is able to improve the accuracy and fairness of their model, even in settings where each party has a model that performs well on their own dataset or when datasets are not IID and model architectures are heterogeneous across parties.
Yu Sun, Jiaming Liu, Yiran Sun, Brendt Wohlberg, Ulugbek Kamilov
tl;dr: Our work develops a novel deep-regularized asynchronous parallel method with provable convergence guarantees for solving large-scale inverse problems.
Regularization by denoising (RED) is a recently developed framework for solving inverse problems by integrating advanced denoisers as image priors. Recent work has shown its state-of-the-art performance when combined with pre-trained deep denoisers. However, current RED algorithms are inadequate for parallel processing on multicore systems. We address this issue by proposing a new{asynchronous RED (Async-RED) algorithm that enables asynchronous parallel processing of data, making it significantly faster than its serial counterparts for large-scale inverse problems. The computational complexity of Async-RED is further reduced by using a random subset of measurements at every iteration. We present a complete theoretical analysis of the algorithm by establishing its convergence under explicit assumptions on the data-fidelity and the denoiser. We validate Async-RED on image recovery using pre-trained deep denoisers as priors.
Allan Zhou, Tom Knowles, Chelsea Finn
tl;dr: A method for automatically meta-learning and encoding equivariances into neural networks.
Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only works when practitioners know the symmetries of the task and can manually construct an architecture with the corresponding equivariances. Our goal is an approach for learning equivariances from data, without needing to design custom task-specific architectures. We present a method for learning and encoding equivariances into networks by learning corresponding parameter sharing patterns from data. Our method can provably represent equivariance-inducing parameter sharing for any finite group of symmetry transformations. Our experiments suggest that it can automatically learn to encode equivariances to common transformations used in image processing tasks.
Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang
tl;dr: Using auxiliary information as inputs hurts OOD, but using auxiliary information by pretraining and self-training improves in-distribution and OOD accuracies on real-world datasets, with theoretical guarantees in a linear multi-task setting.
Consider a prediction setting with few in-distribution labeled examples and many unlabeled examples both in- and out-of-distribution (OOD). The goal is to learn a model which performs well both in-distribution and OOD. In these settings, auxiliary information is often cheaply available for every input. How should we best leverage this auxiliary information for the prediction task? Empirically across three image and time-series datasets, and theoretically in a multi-task linear regression setting, we show that (i) using auxiliary information as input features improves in-distribution error but can hurt OOD error; but (ii) using auxiliary information as outputs of auxiliary pre-training tasks improves OOD error. To get the best of both worlds, we introduce In-N-Out, which first trains a model with auxiliary inputs and uses it to pseudolabel all the in-distribution inputs, then pre-trains a model on OOD auxiliary outputs and fine-tunes this model with the pseudolabels (self-training). We show both theoretically and empirically that In-N-Out outperforms auxiliary inputs or outputs alone on both in-distribution and OOD error.
Vitaly Kurin, Maximilian Igl, Tim Rocktäschel, Wendelin Boehmer, Shimon Whiteson
tl;dr: Transformer-based approach to multitask incompatible continuous control inspired by a hypothesis that any benefits GNNs extract from the graph structure are outweighed by difficulties they create for message passing.
Multitask Reinforcement Learning is a promising way to obtain models with better performance, generalisation, data efficiency, and robustness. Most existing work is limited to compatible settings, where the state and action space dimensions are the same across tasks. Graph Neural Networks (GNN) are one way to address incompatible environments, because they can process graphs of arbitrary size. They also allow practitioners to inject biases encoded in the structure of the input graph. Existing work in graph-based continuous control uses the physical morphology of the agent to construct the input graph, i.e., encoding limb features as node labels and using edges to connect the nodes if their corresponded limbs are physically connected. In this work, we present a series of ablations on existing methods that show that morphological information encoded in the graph does not improve their performance. Motivated by the hypothesis that any benefits GNNs extract from the graph structure are outweighed by difficulties they create for message passing, we also propose Amorpheus, a transformer-based approach. Further results show that, while Amorpheus ignores the morphological information that GNNs encode, it nonetheless substantially outperforms GNN-based methods.
Jake Snell, Richard Zemel
tl;dr: We propose a Gaussian process approach to few-shot classification based on the one-vs-each softmax approximation and Pólya-Gamma augmentation, and demonstrate competitive few-shot accuracy and strong uncertainty quantification.
Few-shot classification (FSC), the task of adapting a classifier to unseen classes given a small labeled dataset, is an important step on the path toward human-like machine learning. Bayesian methods are well-suited to tackling the fundamental issue of overfitting in the few-shot scenario because they allow practitioners to specify prior beliefs and update those beliefs in light of observed data. Contemporary approaches to Bayesian few-shot classification maintain a posterior distribution over model parameters, which is slow and requires storage that scales with model size. Instead, we propose a Gaussian process classifier based on a novel combination of Pólya-Gamma augmentation and the one-vs-each softmax approximation that allows us to efficiently marginalize over functions rather than model parameters. We demonstrate improved accuracy and uncertainty quantification on both standard few-shot classification benchmarks and few-shot domain transfer tasks.
Chao Pan, Siheng Chen, Antonio Ortega
tl;dr: We put forth a novel mathematically designed framework "ST-GST" to analyze spatio-temporal data.
Although spatio-temporal graph neural networks have achieved great empirical success in handling multiple correlated time series, they may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data. Furthermore, spatio-temporal graph neural networks lack theoretical interpretation. To address these issues, we put forth a novel mathematically designed framework to analyze spatio-temporal data. Our proposed spatio-temporal graph scattering transform (ST-GST) extends traditional scattering transform to the spatio-temporal domain. It performs iterative applications of spatio-temporal graph wavelets and nonlinear activation functions, which can be viewed as a forward pass of spatio-temporal graph convolutional networks without training. Since all the filter coefficients in ST-GST are mathematically designed, it is promising for the real-world scenarios with limited training data, and also allows for a theoretical analysis, which shows that the proposed ST-GST is stable to small perturbations of input signals and structures. Finally, our experiments show that i) ST-GST outperforms spatio-temporal graph convolutional networks by an increase of 35% in accuracy for MSR Action3D dataset; ii) it is better and computationally more efficient to design the transform based on separable spatio-temporal graphs than the joint ones; and iii) nonlinearity in ST-GST is critical to empirical performance.
Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, Arnold Overwijk
tl;dr: This paper improves the learning of dense text retrieval using ANCE, which selects global negatives with bigger gradient norms using an asynchronously updated ANN index.
Conducting text retrieval in a learned dense representation space has many intriguing advantages. Yet dense retrieval (DR) often underperforms word-based sparse retrieval. In this paper, we first theoretically show the bottleneck of dense retrieval is the domination of uninformative negatives sampled in mini-batch training, which yield diminishing gradient norms, large gradient variances, and slow convergence. We then propose Approximate nearest neighbor Negative Contrastive Learning (ANCE), which selects hard training negatives globally from the entire corpus. Our experiments demonstrate the effectiveness of ANCE on web search, question answering, and in a commercial search engine, showing ANCE dot-product retrieval nearly matches the accuracy of BERT-based cascade IR pipeline. We also empirically validate our theory that negative sampling with ANCE better approximates the oracle importance sampling procedure and improves learning convergence.
Nikunj Saunshi, Sadhika Malladi, Sanjeev Arora
tl;dr: We develop a mathematical framework for understanding why language model features help with downstream linear classification tasks of interest
Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of this success. This paper initiates a mathematical study of this phenomenon for the downstream task of text classification by considering the following questions: (1) What is the intuitive connection between the pretraining task of next word prediction and text classification? (2) How can we mathematically formalize this connection and quantify the benefit of language modeling? For (1), we hypothesize, and verify empirically, that classification tasks of interest can be reformulated as sentence completion tasks, thus making language modeling a meaningful pretraining task. With a mathematical formalization of this hypothesis, we make progress towards (2) and show that language models that are $\epsilon$-optimal in cross-entropy (log-perplexity) learn features that can linearly solve such classification tasks with $\mathcal{O}(\sqrt{\epsilon})$ error, thus demonstrating that doing well on language modeling can be beneficial for downstream tasks. We experimentally verify various assumptions and theoretical findings, and also use insights from the analysis to design a new objective function that performs well on some classification tasks.
Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu
tl;dr: We propose a non-autoregressive TTS model named FastSpeech 2 to better solve the one-to-many mapping problem in TTS and surpass autoregressive models in voice quality.
Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated and time-consuming, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs in training and use predicted values in inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of fully end-to-end inference. Experimental results show that 1) FastSpeech 2 achieves a 3x training speed-up over FastSpeech, and FastSpeech 2s enjoys even faster inference speed; 2) FastSpeech 2 and 2s outperform FastSpeech in voice quality, and FastSpeech 2 can even surpass autoregressive models. Audio samples are available at
Abdul Fatir Ansari, Ming Liang Ang, Harold Soh
tl;dr: A method of refining samples from deep generative models using the discriminator gradient flow of f-divergences.
Deep generative modeling has seen impressive advances in recent years, to the point where it is now commonplace to see simulated samples (e.g., images) that closely resemble real-world data. However, generation quality is generally inconsistent for any given model and can vary dramatically between samples. We introduce Discriminator Gradient $f$low (DG$f$low), a new technique that improves generated samples via the gradient flow of entropy-regularized $f$-divergences between the real and the generated data distributions. The gradient flow takes the form of a non-linear Fokker-Plank equation, which can be easily simulated by sampling from the equivalent McKean-Vlasov process. By refining inferior samples, our technique avoids wasteful sample rejection used by previous methods (DRS & MH-GAN). Compared to existing works that focus on specific GAN variants, we show our refinement approach can be applied to GANs with vector-valued critics and even other deep generative models such as VAEs and Normalizing Flows. Empirical results on multiple synthetic, image, and text datasets demonstrate that DG$f$low leads to significant improvement in the quality of generated samples for a variety of generative models, outperforming the state-of-the-art Discriminator Optimal Transport (DOT) and Discriminator Driven Latent Sampling (DDLS) methods.
Aayam Kumar Shrestha, Stefan Lee, Prasad Tadepalli, Alan Fern
tl;dr: The paper introduces and investigates an offline RL approach based on optimally solving a finite-state MDP that is derived from the experience dataset using any latent state representation.
We study an approach to offline reinforcement learning (RL) based on optimally solving finitely-represented MDPs derived from a static dataset of experience. This approach can be applied on top of any learned representation and has the potential to easily support multiple solution objectives as well as zero-shot adjustment to changing environments and goals. Our main contribution is to introduce the Deep Averagers with Costs MDP (DAC-MDP) and to investigate its solutions for offline RL. DAC-MDPs are a non-parametric model that can leverage deep representations and account for limited data by introducing costs for exploiting under-represented parts of the model. In theory, we show conditions that allow for lower-bounding the performance of DAC-MDP solutions. We also investigate the empirical behavior in a number of environments, including those with image-based observations. Overall, the experiments demonstrate that the framework can work in practice and scale to large complex offline RL problems.
Jorge A Mendez, ERIC EATON
tl;dr: We create a general-purpose framework for lifelong learning of compositional structures that splits the learning process into two stages: assimilation of new tasks with existing components, and accommodation of new knowledge into the components.
A hallmark of human intelligence is the ability to construct self-contained chunks of knowledge and adequately reuse them in novel combinations for solving different yet structurally related problems. Learning such compositional structures has been a significant challenge for artificial systems, due to the combinatorial nature of the underlying search problem. To date, research into compositional learning has largely proceeded separately from work on lifelong or continual learning. We integrate these two lines of work to present a general-purpose framework for lifelong learning of compositional structures that can be used for solving a stream of related tasks. Our framework separates the learning process into two broad stages: learning how to best combine existing components in order to assimilate a novel problem, and learning how to adapt the set of existing components to accommodate the new problem. This separation explicitly handles the trade-off between the stability required to remember how to solve earlier tasks and the flexibility required to solve new tasks, as we show empirically in an extensive evaluation.
Arash Tavakoli, Mehdi Fatemi, Petar Kormushev
tl;dr: This paper introduces a class of models, called action hypergraph networks, for action-value estimation by leveraging the combinatorial structure of multi-dimensional discrete action spaces.
Action-value estimation is a critical component of many reinforcement learning (RL) methods whereby sample complexity relies heavily on how fast a good estimator for action value can be learned. By viewing this problem through the lens of representation learning, good representations of both state and action can facilitate action-value estimation. While advances in deep learning have seamlessly driven progress in learning state representations, given the specificity of the notion of agency to RL, little attention has been paid to learning action representations. We conjecture that leveraging the combinatorial structure of multi-dimensional action spaces is a key ingredient for learning good representations of action. To test this, we set forth the action hypergraph networks framework---a class of functions for learning action representations in multi-dimensional discrete action spaces with a structural inductive bias. Using this framework we realise an agent class based on a combination with deep Q-networks, which we dub hypergraph Q-networks. We show the effectiveness of our approach on a myriad of domains: illustrative prediction problems under minimal confounding effects, Atari 2600 games, and discretised physical control benchmarks.
Lu Liu, William L. Hamilton, Guodong Long, Jing Jiang, Hugo Larochelle
tl;dr: code at:
Few-shot classification aims to recognize unseen classes when presented with only a small number of samples. We consider the problem of multi-domain few-shot image classification, where unseen classes and examples come from diverse data sources. This problem has seen growing interest and has inspired the development of benchmarks such as Meta-Dataset. A key challenge in this multi-domain setting is to effectively integrate the feature representations from the diverse set of training domains. Here, we propose a Universal Representation Transformer (URT) layer, that meta-learns to leverage universal features for few-shot classification by dynamically re-weighting and composing the most appropriate domain-specific representations. In experiments, we show that URT sets a new state-of-the-art result on Meta-Dataset. Specifically, it achieves top-performance on the highest number of data sources compared to competing methods. We analyze variants of URT and present a visualization of the attention score heatmaps that sheds light on how the model performs cross-domain generalization.
Wonseok Jeon, Chen-Yang Su, Paul Barde, Thang Doan, Derek Nowrouzezahrai, Joelle Pineau
tl;dr: We propose tractable solutions of regularized IRL and algorithms to acquire those solutions.
Inverse Reinforcement Learning (IRL) aims to facilitate a learner’s ability to imitate expert behavior by acquiring reward functions that explain the expert’s decisions. Regularized IRLapplies strongly convex regularizers to the learner’s policy in order to avoid the expert’s behavior being rationalized by arbitrary constant rewards, also known as degenerate solutions. We propose tractable solutions, and practical methods to obtain them, for regularized IRL. Current methods are restricted to the maximum-entropy IRL framework, limiting them to Shannon-entropy regularizers, as well as proposing solutions that are intractable in practice. We present theoretical backing for our proposed IRL method’s applicability to both discrete and continuous controls, empirically validating our performance on a variety of tasks.
Kyle Aitken, Vinay Venkatesh Ramasesh, Ankush Garg, Yuan Cao, David Sussillo, Niru Maheswaranathan
tl;dr: We study text classification RNNs using tools from dynamical systems analysis, finding and explaining the geometry of low-dimensional attractor manifolds.
Despite the widespread application of recurrent neural networks (RNNs), a unified understanding of how RNNs solve particular tasks remains elusive. In particular, it is unclear what dynamical patterns arise in trained RNNs, and how those pat-terns depend on the training dataset or task. This work addresses these questions in the context of text classification, building on earlier work studying the dynamics of binary sentiment-classification networks (Maheswaranathan et al., 2019). We study text-classification tasks beyond the binary case, exploring the dynamics ofRNNs trained on both natural and synthetic datasets. These dynamics, which we find to be both interpretable and low-dimensional, share a common mechanism across architectures and datasets: specifically, these text-classification networks use low-dimensional attractor manifolds to accumulate evidence for each class as they process the text. The dimensionality and geometry of the attractor manifold are determined by the structure of the training dataset, with the dimensionality reflecting the number of scalar quantities the network remembers in order to classify.In categorical classification, for example, we show that this dimensionality is one less than the number of classes. Correlations in the dataset, such as those induced by ordering, can further reduce the dimensionality of the attractor manifold; we show how to predict this reduction using simple word-count statistics computed on the training dataset. To the degree that integration of evidence towards a decision is a common computational primitive, this work continues to lay the foundation for using dynamical systems techniques to study the inner workings of RNNs.
Sergei Ivanov, Liudmila Prokhorenkova
tl;dr: A novel strong architecture that combines advantages of GBDT and GNN for node-level prediction problems on graphs with tabular data.
Graph neural networks (GNNs) are powerful models that have been successful in various graph representation learning tasks. Whereas gradient boosted decision trees (GBDT) often outperform other machine learning methods when faced with heterogeneous tabular data. But what approach should be used for graphs with tabular node features? Previous GNN models have mostly focused on networks with homogeneous sparse features and, as we show, are suboptimal in the heterogeneous setting. In this work, we propose a novel architecture that trains GBDT and GNN jointly to get the best of both worlds: the GBDT model deals with heterogeneous features, while GNN accounts for the graph structure. Our model benefits from end-to-end optimization by allowing new trees to fit the gradient updates of GNN. With an extensive experimental comparison to the leading GBDT and GNN models, we demonstrate a significant increase in performance on a variety of graphs with tabular features. The code is available:
Yuhuai Wu, Albert Jiang, Jimmy Ba, Roger Baker Grosse
tl;dr: We introduce INT, a synthetic INequality Theorem proving benchmark, to tackle the data sparsity and out-of-distribution problems for theorem proving and benchmarked transformer-based and GNN-based agents' generalization performance.
In learning-assisted theorem proving, one of the most critical challenges is to generalize to theorems unlike those seen at training time. In this paper, we introduce INT, an INequality Theorem proving benchmark designed to test agents’ generalization ability. INT is based on a theorem generator, which provides theoretically infinite data and allows us to measure 6 different types of generalization, each reflecting a distinct challenge, characteristic of automated theorem proving. In addition, provides a fast theorem proving environment with sequence-based and graph-based interfaces, conducive to performing learning-based research. We introduce base-lines with architectures including transformers and graph neural networks (GNNs)for INT. Using INT, we find that transformer-based agents achieve stronger test performance for most of the generalization tasks, despite having much larger out-of-distribution generalization gaps than GNNs. We further find that the addition of Monte Carlo Tree Search (MCTS) at test time helps to prove new theorems.
Mengye Ren, Michael Louis Iuzzolino, Michael Curtis Mozer, Richard Zemel
tl;dr: We propose a new continual few-shot learning paradigm and a new model.
We aim to bridge the gap between typical human and machine-learning environments by extending the standard framework of few-shot learning to an online, continual setting. In this setting, episodes do not have separate training and testing phases, and instead models are evaluated online while learning novel classes. As in the real world, where the presence of spatiotemporal context helps us retrieve learned skills in the past, our online few-shot learning setting also features an underlying context that changes throughout time. Object classes are correlated within a context and inferring the correct context can lead to better performance. Building upon this setting, we propose a new few-shot learning dataset based on large scale indoor imagery that mimics the visual experience of an agent wandering within a world. Furthermore, we convert popular few-shot learning approaches into online versions and we also propose a new model that can make use of spatiotemporal contextual information from the recent past.
Honglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf
tl;dr: We propose Hopper, Multi-Hop Transformer, and CATER-h dataset to approach object-centric spatiotemporal reasoning in videos.
This paper considers the problem of spatiotemporal object-centric reasoning in videos. Central to our approach is the notion of object permanence, i.e., the ability to reason about the location of objects as they move through the video while being occluded, contained or carried by other objects. Existing deep learning based approaches often suffer from spatiotemporal biases when applied to video reasoning problems. We propose Hopper, which uses a Multi-hop Transformer for reasoning object permanence in videos. Given a video and a localization query, Hopper reasons over image and object tracks to automatically hop over critical frames in an iterative fashion to predict the final position of the object of interest. We demonstrate the effectiveness of using a contrastive loss to reduce spatiotemporal biases. We evaluate over CATER dataset and find that Hopper achieves 73.2% Top-1 accuracy using just 1 FPS by hopping through just a few critical frames. We also demonstrate Hopper can perform long-term reasoning by building a CATER-h dataset that requires multi-step reasoning to localize objects of interest correctly.
Fredrik Carlsson, Amaru Cuba Gyllensten, Evangelia Gogoulou, Erik Ylipää Hellqvist, Magnus Sahlgren
tl;dr: A self-supervised method for learning STS related sentence embedding using pre-trained language models, setting a new SOTA for STS related embedding tasks.
Extracting semantically useful natural language sentence representations from pre-trained deep neural networks such as Transformers remains a challenge. We first demonstrate that pre-training objectives impose a significant task bias onto the final layers of models with a layer-wise survey of the Semantic Textual Similarity (STS) correlations for multiple common Transformer language models. We then propose a new self-supervised method called Contrastive Tension (CT) to counter such biases. CT frames the training objective as a noise-contrastive task between the final layer representations of two independent models, in turn making the final layer representations suitable for feature extraction. Results from multiple common unsupervised and supervised STS tasks indicate that CT outperforms previous State Of The Art (SOTA), and when combining CT with supervised data we improve upon previous SOTA results with large margins.
Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber
tl;dr: We present a Recurrent Neural Network model which is augmented with an associative memory to generalise in a more systematically
Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. To this end, we augment the LSTM model with an associative memory, dubbed \textit{Fast Weight Memory} (FWM). Through differentiable operations at every step of a given input sequence, the LSTM \textit{updates and maintains} compositional associations stored in the rapidly changing FWM weights. Our model is trained end-to-end by gradient descent and yields excellent performance on compositional language reasoning problems, meta-reinforcement-learning for POMDPs, and small-scale word-level language modelling.
Xinyue Chen, Che Wang, Zijian Zhou, Keith W. Ross
tl;dr: We propose and analyze a novel model-free algorithm that achieves strong performance with a high update-to-data ratio.
Using a high Update-To-Data (UTD) ratio, model-based methods have recently achieved much higher sample efficiency than previous model-free methods for continuous-action DRL benchmarks. In this paper, we introduce a simple model-free algorithm, Randomized Ensembled Double Q-Learning (REDQ), and show that its performance is just as good as, if not better than, a state-of-the-art model-based algorithm for the MuJoCo benchmark. Moreover, REDQ can achieve this performance using fewer parameters than the model-based method, and with less wall-clock run time. REDQ has three carefully integrated ingredients which allow it to achieve its high performance: (i) a UTD ratio $\gg 1$; (ii) an ensemble of Q functions; (iii) in-target minimization across a random subset of Q functions from the ensemble. Through carefully designed experiments, we provide a detailed analysis of REDQ and related model-free algorithms. To our knowledge, REDQ is the first successful model-free DRL algorithm for continuous-action spaces using a UTD ratio $\gg 1$.
Jiayi Shen, Haotao Wang, Shupeng Gui, Jianchao Tan, Zhangyang Wang, Ji Liu
tl;dr: We propose a unified model and embedding compression (UMEC) framework to hammer an efficient neural network-based recommendation system.
The recommendation system (RS) plays an important role in the content recommendation and retrieval scenarios. The core part of the system is the Ranking neural network, which is usually a bottleneck of whole system performance during online inference. In this work, we propose a unified model and embedding compression (UMEC) framework to hammer an efficient neural network-based recommendation system. Our framework jointly learns input feature selection and neural network compression together, and solve them as an end-to-end resource-constrained optimization problem using ADMM. Our method outperforms other baselines in terms of neural network Flops, sparse embedding feature size and the number of sparse embedding features. We evaluate our method on the public benchmark of DLRM, trained over the Kaggle Criteo dataset. The codes can be found at
Shuang Ma, Zhaoyang Zeng, Daniel McDuff, Yale Song
tl;dr: We propose an active learning approach to improve negative sampling for contrastive learning and demonstrate it on learning audio-visual representations from videos.
Contrastive learning has been shown to produce generalizable representations of audio and visual data by maximizing the lower bound on the mutual information (MI) between different views of an instance. However, obtaining a tight lower bound requires a sample size exponential in MI and thus a large set of negative samples. We can incorporate more samples by building a large queue-based dictionary, but there are theoretical limits to performance improvements even with a large number of negative samples. We hypothesize that random negative sampling leads to a highly redundant dictionary that results in suboptimal representations for downstream tasks. In this paper, we propose an active contrastive learning approach that builds an actively sampled dictionary with diverse and informative items, which improves the quality of negative samples and improves performances on tasks where there is high mutual information in the data, e.g., video classification. Our model achieves state-of-the-art performance on challenging audio and visual downstream benchmarks including UCF101, HMDB51 and ESC50.
Weitong ZHANG, Dongruo Zhou, Lihong Li, Quanquan Gu
tl;dr: We propose NeuralTS, a provable neural work-based Thompson sampling algorithm for stochastic contextual bandits.
Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both exploration and exploitation. At the core of our algorithm is a novel posterior distribution of the reward, where its mean is the neural network approximator, and its variance is built upon the neural tangent features of the corresponding neural network. We prove that, provided the underlying reward function is bounded, the proposed algorithm is guaranteed to achieve a cumulative regret of $O(T^{1/2})$, which matches the regret of other contextual bandit algorithms in terms of total round number $T$. Experimental comparisons with other benchmark bandit algorithms on various data sets corroborate our theory.
Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma
tl;dr: Optimal regularization can provably avoid double-descent in certain settings.
Recent empirical and theoretical studies have shown that many learning algorithms -- from linear regression to neural networks -- can have test performance that is non-monotonic in quantities such the sample size and model size. This striking phenomenon, often referred to as "double descent", has raised questions of if we need to re-think our current understanding of generalization. In this work, we study whether the double-descent phenomenon can be avoided by using optimal regularization. Theoretically, we prove that for certain linear regression models with isotropic data distribution, optimally-tuned $\ell_2$ regularization achieves monotonic test performance as we grow either the sample size or the model size. We also demonstrate empirically that optimally-tuned $\ell_2$ regularization can mitigate double descent for more general models, including neural networks. Our results suggest that it may also be informative to study the test risk scalings of various algorithms in the context of appropriately tuned regularization.
Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville, Philip Bachman
tl;dr: We propose a temporal, self-supervised objective for RL agents and show that it significantly improves data efficiency in a setting limited to just 2h of gameplay on Atari.
While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interaction with the environment, learning from limited interaction remains a key challenge. We posit that an agent can learn more efficiently if we augment reward maximization with self-supervised objectives based on structure in its visual input and sequential interaction with the environment. Our method, Self-Predictive Representations (SPR), trains an agent to predict its own latent state representations multiple steps into the future. We compute target representations for future states using an encoder which is an exponential moving average of the agent’s parameters and we make predictions using a learned transition model. On its own, this future prediction objective outperforms prior methods for sample-efficient deep RL from pixels. We further improve performance by adding data augmentation to the future prediction loss, which forces the agent’s representations to be consistent across multiple views of an observation. Our full self-supervised objective, which combines future prediction and data augmentation, achieves a median human-normalized score of 0.415 on Atari in a setting limited to 100k steps of environment interaction, which represents a 55% relative improvement over the previous state-of-the-art. Notably, even in this limited data regime, SPR exceeds expert human scores on 7 out of 26 games. We’ve made the code associated with this work available at
Jiaheng Wei, Yang Liu
tl;dr: We show when maximizing a properly defined $f$-divergence measure with respect to a classifier's predictions and the supervised labels is robust with label noise.
We show when maximizing a properly defined $f$-divergence measure with respect to a classifier's predictions and the supervised labels is robust with label noise. Leveraging its variational form, we derive a nice decoupling property for a family of $f$-divergence measures when label noise presents, where the divergence is shown to be a linear combination of the variational difference defined on the clean distribution and a bias term introduced due to the noise. The above derivation helps us analyze the robustness of different $f$-divergence functions. With established robustness, this family of $f$-divergence functions arises as useful metrics for the problem of learning with noisy labels, which do not require the specification of the labels' noise rate. When they are possibly not robust, we propose fixes to make them so. In addition to the analytical results, we present thorough experimental evidence. Our code is available at
Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Cong Hao, Yingyan Lin
tl;dr: A Hardware-Aware Neural Architecture Search Benchmark
HardWare-aware Neural Architecture Search (HW-NAS) has recently gained tremendous attention by automating the design of deep neural networks deployed in more resource-constrained daily life devices. Despite its promising performance, developing optimal HW-NAS solutions can be prohibitively challenging as it requires cross-disciplinary knowledge in the algorithm, micro-architecture, and device-specific compilation. First, to determine the hardware-cost to be incorporated into the NAS process, existing works mostly adopt either pre-collected hardware-cost look-up tables or device-specific hardware-cost models. The former can be time-consuming due to the required knowledge of the device’s compilation method and how to set up the measurement pipeline, while building the latter is often a barrier for non-hardware experts like NAS researchers. Both of them limit the development of HW-NAS innovations and impose a barrier-to-entry to non-hardware experts. Second, similar to generic NAS, it can be notoriously difficult to benchmark HW-NAS algorithms due to their significant required computational resources and the differences in adopted search spaces, hyperparameters, and hardware devices. To this end, we develop HW-NAS-Bench, the first public dataset for HW-NAS research which aims to democratize HW-NAS research to non-hardware experts and make HW-NAS research more reproducible and accessible. To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance (e.g., energy cost and latency) of all the networks in the search spaces of both NAS-Bench-201 and FBNet, on six hardware devices that fall into three categories (i.e., commercial edge devices, FPGA, and ASIC). Furthermore, we provide a comprehensive analysis of the collected measurements in HW-NAS-Bench to provide insights for HW-NAS research. Finally, we demonstrate exemplary user cases to (1) show that HW-NAS-Bench allows non-hardware experts to perform HW-NAS by simply querying our pre-measured dataset and (2) verify that dedicated device-specific HW-NAS can indeed lead to optimal accuracy-cost trade-offs. The codes and all collected data are available at
Huan Zhang, Hongge Chen, Duane S Boning, Cho-Jui Hsieh
tl;dr: We study the robustness of RL agents under perturbations on states and find that using an "optimal" adversary learned online in an alternating training manner can improve the robustness of agent policy.
We study the robustness of reinforcement learning (RL) with adversarially perturbed state observations, which aligns with the setting of many adversarial attacks to deep reinforcement learning (DRL) and is also important for rolling out real-world RL agent under unpredictable sensing noise. With a fixed agent policy, we demonstrate that an optimal adversary to perturb state observations can be found, which is guaranteed to obtain the worst case agent reward. For DRL settings, this leads to a novel empirical adversarial attack to RL agents via a learned adversary that is much stronger than previous ones. To enhance the robustness of an agent, we propose a framework of alternating training with learned adversaries (ATLA), which trains an adversary online together with the agent using policy gradient following the optimal adversarial attack framework. Additionally, inspired by the analysis of state-adversarial Markov decision process (SA-MDP), we show that past states and actions (history) can be useful for learning a robust agent, and we empirically find a LSTM based policy can be more robust under adversaries. Empirical evaluations on a few continuous control environments show that ATLA achieves state-of-the-art performance under strong adversaries. Our code is available at
Benyou Wang, Lifeng Shang, Christina Lioma, Xin Jiang, Hao Yang, Qun Liu, Jakob Grue Simonsen
tl;dr: This paper amis to understand and evaluate position embeddings, especially in pretrain language models
Various Position Embeddings (PEs) have been proposed in Transformer based architectures~(e.g. BERT) to model word order. These are empirically-driven and perform well, but no formal framework exists to systematically study them. To address this, we present three properties of PEs that capture word distance in vector space: translation invariance, monotonicity, and symmetry. These properties formally capture the behaviour of PEs and allow us to reinterpret sinusoidal PEs in a principled way. Moreover, we propose a new probing test (called `identical word probing') and mathematical indicators to quantitatively detect the general attention patterns with respect to the above properties. An empirical evaluation of seven PEs (and their combinations) for classification (GLUE) and span prediction (SQuAD) shows that: (1) both classification and span prediction benefit from translation invariance and local monotonicity, while symmetry slightly decreases performance; (2) The fully-learnable absolute PE performs better in classification, while relative PEs perform better in span prediction. We contribute the first formal and quantitative analysis of desiderata for PEs, and a principled discussion about their correlation to the performance of typical downstream tasks.
Ziang Yan, Yiwen Guo, Jian Liang, Changshui Zhang
tl;dr: A novel hard-label black-box adversarial attack that introduces a reinforcement learning based formulation with a pre-trained policy network
To craft black-box adversarial examples, adversaries need to query the victim model and take proper advantage of its feedback. Existing black-box attacks generally suffer from high query complexity, especially when only the top-1 decision (i.e., the hard-label prediction) of the victim model is available. In this paper, we propose a novel hard-label black-box attack named Policy-Driven Attack, to reduce the query complexity. Our core idea is to learn promising search directions of the adversarial examples using a well-designed policy network in a novel reinforcement learning formulation, in which the queries become more sensible. Experimental results demonstrate that our method can significantly reduce the query complexity in comparison with existing state-of-the-art hard-label black-box attacks on various image classification benchmark datasets. Code and models for reproducing our results are available at
Kaidi Cao, Yining Chen, Junwei Lu, Nikos Arechiga, Adrien Gaidon, Tengyu Ma
tl;dr: We propose a data-dependent regularization technique for learning heteroskedastic and imbalanced datasets.
Real-world large-scale datasets are heteroskedastic and imbalanced --- labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imbalance challenge deep learning algorithms due to the difficulty of distinguishing among mislabeled, ambiguous, and rare examples. Addressing heteroskedasticity and imbalance simultaneously is under-explored. We propose a data-dependent regularization technique for heteroskedastic datasets that regularizes different regions of the input space differently. Inspired by the theoretical derivation of the optimal regularization strength in a one-dimensional nonparametric classification setting, our approach adaptively regularizes the data points in higher-uncertainty, lower-density regions more heavily. We test our method on several benchmark tasks, including a real-world heteroskedastic and imbalanced dataset, WebVision. Our experiments corroborate our theory and demonstrate a significant improvement over other methods in noise-robust deep learning.
Joseph D Viviano, Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen
tl;dr: We controlled feature construction on images using masks to help models generalize to test distributions with covariate shift and noticed that it didn't affect the saliency maps in the way one would expect even though it improved generalization.
Poor generalization is one symptom of models that learn to predict target variables using spuriously-correlated image features present only in the training distribution instead of the true image features that denote a class. It is often thought that this can be diagnosed visually using attribution (aka saliency) maps. We study if this assumption is correct. In some prediction tasks, such as for medical images, one may have some images with masks drawn by a human expert, indicating a region of the image containing relevant information to make the prediction. We study multiple methods that take advantage of such auxiliary labels, by training networks to ignore distracting features which may be found outside of the region of interest. This mask information is only used during training and has an impact on generalization accuracy depending on the severity of the shift between the training and test distributions. Surprisingly, while these methods improve generalization performance in the presence of a covariate shift, there is no strong correspondence between the correction of attribution towards the features a human expert have labelled as important and generalization performance. These results suggest that the root cause of poor generalization may not always be spatially defined, and raise questions about the utility of masks as 'attribution priors' as well as saliency maps for explainable predictions.
Samuel Horváth, Peter Richtarik
Modern large-scale machine learning applications require stochastic optimization algorithms to be implemented on distributed computing systems. A key bottleneck of such systems is the communication overhead for exchanging information across the workers, such as stochastic gradients. Among the many techniques proposed to remedy this issue, one of the most successful is the framework of compressed communication with error feedback (EF). EF remains the only known technique that can deal with the error induced by contractive compressors which are not unbiased, such as Top-$K$ or PowerSGD. In this paper, we propose a new and theoretically and practically better alternative to EF for dealing with contractive compressors. In particular, we propose a construction which can transform any contractive compressor into an induced unbiased compressor. Following this transformation, existing methods able to work with unbiased compressors can be applied. We show that our approach leads to vast improvements over EF, including reduced memory requirements, better communication complexity guarantees and fewer assumptions. We further extend our results to federated learning with partial participation following an arbitrary distribution over the nodes and demonstrate the benefits thereof. We perform several numerical experiments which validate our theoretical findings.
Soheil Kolouri, Navid Naderializadeh, Gustavo K. Rohde, Heiko Hoffmann
tl;dr: Wasserstein Embedding for Graph Learning (WEGL) is a novel and fast framework for embedding entire graphs into a vector space in which the Euclidean distance between representations approximates the 2-Wasserstein distance.
We present Wasserstein Embedding for Graph Learning (WEGL), a novel and fast framework for embedding entire graphs in a vector space, in which various machine learning models are applicable for graph-level prediction tasks. We leverage new insights on defining similarity between graphs as a function of the similarity between their node embedding distributions. Specifically, we use the Wasserstein distance to measure the dissimilarity between node embeddings of different graphs. Unlike prior work, we avoid pairwise calculation of distances between graphs and reduce the computational complexity from quadratic to linear in the number of graphs. WEGL calculates Monge maps from a reference distribution to each node embedding and, based on these maps, creates a fixed-sized vector representation of the graph. We evaluate our new graph embedding approach on various benchmark graph-property prediction tasks, showing state-of-the-art classification performance while having superior computational efficiency. The code is available at
Daochen Zha, Wenye Ma, Lei Yuan, Xia Hu, Ji Liu
tl;dr: Encouraging exploration via ranking the past episodes and reproducing past good exploration behaviors with imitation learning.
Exploration under sparse reward is a long-standing challenge of model-free reinforcement learning. The state-of-the-art methods address this challenge by introducing intrinsic rewards to encourage exploration in novel states or uncertain environment dynamics. Unfortunately, methods based on intrinsic rewards often fall short in procedurally-generated environments, where a different environment is generated in each episode so that the agent is not likely to visit the same state more than once. Motivated by how humans distinguish good exploration behaviors by looking into the entire episode, we introduce RAPID, a simple yet effective episode-level exploration method for procedurally-generated environments. RAPID regards each episode as a whole and gives an episodic exploration score from both per-episode and long-term views. Those highly scored episodes are treated as good exploration behaviors and are stored in a small ranking buffer. The agent then imitates the episodes in the buffer to reproduce the past good exploration behaviors. We demonstrate our method on several procedurally-generated MiniGrid environments, a first-person-view 3D Maze navigation task from MiniWorld, and several sparse MuJoCo tasks. The results show that RAPID significantly outperforms the state-of-the-art intrinsic reward strategies in terms of sample efficiency and final performance. The code is available at
Andy Shih, Arjun Sawhney, Jovana Kondic, Stefano Ermon, Dorsa Sadigh
tl;dr: Training agents that can adapt to new settings in multi-agent games.
Humans can quickly adapt to new partners in collaborative tasks (e.g. playing basketball), because they understand which fundamental skills of the task (e.g. how to dribble, how to shoot) carry over across new partners. Humans can also quickly adapt to similar tasks with the same partners by carrying over conventions that they have developed (e.g. raising hand signals pass the ball), without learning to coordinate from scratch. To collaborate seamlessly with humans, AI agents should adapt quickly to new partners and new tasks as well. However, current approaches have not attempted to distinguish between the complexities intrinsic to a task and the conventions used by a partner, and more generally there has been little focus on leveraging conventions for adapting to new settings. In this work, we propose a learning framework that teases apart rule-dependent representation from convention-dependent representation in a principled way. We show that, under some assumptions, our rule-dependent representation is a sufficient statistic of the distribution over best-response strategies across partners. Using this separation of representations, our agents are able to adapt quickly to new partners, and to coordinate with old partners on new tasks in a zero-shot manner. We experimentally validate our approach on three collaborative tasks varying in complexity: a contextual multi-armed bandit, a block placing task, and the card game Hanabi.
Kiana Ehsani, Daniel Gordon, Thomas Hai Dang Nguyen, Roozbeh Mottaghi, Ali Farhadi
tl;dr: We learn a muscly-supervised visual representation from human's interactions with the visual world.
Learning effective representations of visual data that generalize to a variety of downstream tasks has been a long quest for computer vision. Most representation learning approaches rely solely on visual data such as images or videos. In this paper, we explore a novel approach, where we use human interaction and attention cues to investigate whether we can learn better representations compared to visual-only representations. For this study, we collect a dataset of human interactions capturing body part movements and gaze in their daily lives. Our experiments show that our ``"muscly-supervised" representation that encodes interaction and attention cues outperforms a visual-only state-of-the-art method MoCo (He et al.,2020), on a variety of target tasks: scene classification (semantic), action recognition (temporal), depth estimation (geometric), dynamics prediction (physics) and walkable surface estimation (affordance). Our code and dataset are available at:
Elan Rosenfeld, Pradeep Kumar Ravikumar, Andrej Risteski
tl;dr: We formally demonstrate that Invariant Risk Minimization and related alternative objectives often perform no better than standard ERM.
Invariant Causal Prediction (Peters et al., 2016) is a technique for out-of-distribution generalization which assumes that some aspects of the data distribution vary across the training set but that the underlying causal mechanisms remain constant. Recently, Arjovsky et al. (2019) proposed Invariant Risk Minimization (IRM), an objective based on this idea for learning deep, invariant features of data which are a complex function of latent variables; many alternatives have subsequently been suggested. However, formal guarantees for all of these works are severely lacking. In this paper, we present the first analysis of classification under the IRM objective—as well as these recently proposed alternatives—under a fairly natural and general model. In the linear case, we show simple conditions under which the optimal solution succeeds or, more often, fails to recover the optimal invariant predictor. We furthermore present the very first results in the non-linear regime: we demonstrate that IRM can fail catastrophically unless the test data is sufficiently similar to the training distribution—this is precisely the issue that it was intended to solve. Thus, in this setting we find that IRM and its alternatives fundamentally do not improve over standard Empirical Risk Minimization.
Justin Bayer, Maximilian Soelch, Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt
tl;dr: We show how a common model assumption in amortised variational inference with sequential LVMS leads to a suboptimality and how to prevent it.
Amortised inference enables scalable learning of sequential latent-variable models (LVMs) with the evidence lower bound (ELBO). In this setting, variational posteriors are often only partially conditioned. While the true posteriors depend, e.g., on the entire sequence of observations, approximate posteriors are only informed by past observations. This mimics the Bayesian filter---a mixture of smoothing posteriors. Yet, we show that the ELBO objective forces partially-conditioned amortised posteriors to approximate products of smoothing posteriors instead. Consequently, the learned generative model is compromised. We demonstrate these theoretical findings in three scenarios: traffic flow, handwritten digits, and aerial vehicle dynamics. Using fully-conditioned approximate posteriors, performance improves in terms of generative modelling and multi-step prediction.
Ziyu Yao, Frank F. Xu, Pengcheng Yin, Huan Sun, Graham Neubig
tl;dr: A generic incremental editing model for tree-structured data
While most neural generative models generate outputs in a single pass, the human creative process is usually one of iterative building and refinement. Recent work has proposed models of editing processes, but these mostly focus on editing sequential data and/or only model a single editing pass. In this paper, we present a generic model for incremental editing of structured data (i.e. ''structural edits''). Particularly, we focus on tree-structured data, taking abstract syntax trees of computer programs as our canonical example. Our editor learns to iteratively generate tree edits (e.g. deleting or adding a subtree) and applies them to the partially edited data, thereby the entire editing process can be formulated as consecutive, incremental tree transformations. To show the unique benefits of modeling tree edits directly, we further propose a novel edit encoder for learning to represent edits, as well as an imitation learning method that allows the editor to be more robust. We evaluate our proposed editor on two source code edit datasets, where results show that, with the proposed edit encoder, our editor significantly improves accuracy over previous approaches that generate the edited program directly in one pass. Finally, we demonstrate that training our editor to imitate experts and correct its mistakes dynamically can further improve its performance.
Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang, Haipeng Luo
tl;dr: We prove Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update (OMWU) converge exponentially fast to the Nash equilibrium in the sense of last-iterate in various game settings including matrix games.
Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update (OMWU) for saddle-point optimization have received growing attention due to their favorable last-iterate convergence. However, their behaviors for simple bilinear games over the probability simplex are still not fully understood --- previous analysis lacks explicit convergence rates, only applies to an exponentially small learning rate, or requires additional assumptions such as the uniqueness of the optimal solution. In this work, we significantly expand the understanding of last-iterate convergence for OGDA and OMWU in the constrained setting. Specifically, for OMWU in bilinear games over the simplex, we show that when the equilibrium is unique, linear last-iterate convergence is achievable with a constant learning rate, which improves the result of (Daskalakis & Panageas, 2019) under the same assumption. We then significantly extend the results to more general objectives and feasible sets for the projected OGDA algorithm, by introducing a sufficient condition under which OGDA exhibits concrete last-iterate convergence rates with a constant learning rate. We show that bilinear games over any polytope satisfy this condition and OGDA converges exponentially fast even without the unique equilibrium assumption. Our condition also holds for strongly-convex-strongly-concave functions, recovering the result of (Hsieh et al., 2019). Finally, we provide experimental results to further support our theory.
Cassidy Laidlaw, Sahil Singla, Soheil Feizi
tl;dr: Adversarial training against a perceptually-aligned attack gives high robustness against many diverse adversarial threat models.
A key challenge in adversarial robustness is the lack of a precise mathematical characterization of human perception, used in the definition of adversarial attacks that are imperceptible to human eyes. Most current attacks and defenses try to get around this issue by considering restrictive adversarial threat models such as those bounded by $L_2$ or $L_\infty$ distance, spatial perturbations, etc. However, models that are robust against any of these restrictive threat models are still fragile against other threat models, i.e. they have poor generalization to unforeseen attacks. Moreover, even if a model is robust against the union of several restrictive threat models, it is still susceptible to other imperceptible adversarial examples that are not contained in any of the constituent threat models. To resolve these issues, we propose adversarial training against the set of all imperceptible adversarial examples. Since this set is intractable to compute without a human in the loop, we approximate it using deep neural networks. We call this threat model the neural perceptual threat model (NPTM); it includes adversarial examples with a bounded neural perceptual distance (a neural network-based approximation of the true perceptual distance) to natural images. Through an extensive perceptual study, we show that the neural perceptual distance correlates well with human judgements of perceptibility of adversarial examples, validating our threat model. Under the NPTM, we develop novel perceptual adversarial attacks and defenses. Because the NPTM is very broad, we find that Perceptual Adversarial Training (PAT) against a perceptual attack gives robustness against many other types of adversarial attacks. We test PAT on CIFAR-10 and ImageNet-100 against five diverse adversarial attacks: $L_2$, $L_\infty$, spatial, recoloring, and JPEG. We find that PAT achieves state-of-the-art robustness against the union of these five attacks—more than doubling the accuracy over the next best model—without training against any of them. That is, PAT generalizes well to unforeseen perturbation types. This is vital in sensitive applications where a particular threat model cannot be assumed, and to the best of our knowledge, PAT is the first adversarial training defense with this property. Code and data are available at
Kartik Ahuja, Jun Wang, Amit Dhurandhar, Karthikeyan Shanmugam, Kush R. Varshney
tl;dr: In this work, we provide a sample complexity comparison of the recent invariant risk minimization (IRM) framework with the classic empirical risk minimization (ERM) to answer when is IRM better than ERM in terms of out-of-distribution generalization?
Recently, invariant risk minimization (IRM) was proposed as a promising solution to address out-of-distribution (OOD) generalization. However, it is unclear when IRM should be preferred over the widely-employed empirical risk minimization (ERM) framework. In this work, we analyze both these frameworks from the perspective of sample complexity, thus taking a firm step towards answering this important question. We find that depending on the type of data generation mechanism, the two approaches might have very different finite sample and asymptotic behavior. For example, in the covariate shift setting we see that the two approaches not only arrive at the same asymptotic solution, but also have similar finite sample behavior with no clear winner. For other distribution shifts such as those involving confounders or anti-causal variables, however, the two approaches arrive at different asymptotic solutions where IRM is guaranteed to be close to the desired OOD solutions in the finite sample regime, while ERM is biased even asymptotically. We further investigate how different factors --- the number of environments, complexity of the model, and IRM penalty weight --- impact the sample complexity of IRM in relation to its distance from the OOD solutions.
Michael Sejr Schlichtkrull, Nicola De Cao, Ivan Titov
tl;dr: We present a novel post-hoc interpretation method for graph neural networks, and apply it to analyse two models from the NLP literature.
Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. However, there has been little work on interpreting them, and specifically on understanding which parts of the graphs (e.g. syntactic trees or co-reference structures) contribute to a prediction. In this work, we introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. Given a trained GNN model, we learn a simple classifier that, for every edge in every layer, predicts if that edge can be dropped. We demonstrate that such a classifier can be trained in a fully differentiable fashion, employing stochastic gates and encouraging sparsity through the expected $L_0$ norm. We use our technique as an attribution method to analyze GNN models for two tasks -- question answering and semantic role labeling -- providing insights into the information flow in these models. We show that we can drop a large proportion of edges without deteriorating the performance of the model, while we can analyse the remaining edges for interpreting model predictions.
Jonathan Cornford, Damjan Kalajdzievski, Marco Leite, Amélie Lamarquette, Dimitri Michael Kullmann, Blake Aaron Richards
The units in artificial neural networks (ANNs) can be thought of as abstractions of biological neurons, and ANNs are increasingly used in neuroscience research. However, there are many important differences between ANN units and real neurons. One of the most notable is the absence of Dale's principle, which ensures that biological neurons are either exclusively excitatory or inhibitory. Dale's principle is typically left out of ANNs because its inclusion impairs learning. This is problematic, because one of the great advantages of ANNs for neuroscience research is their ability to learn complicated, realistic tasks. Here, by taking inspiration from feedforward inhibitory interneurons in the brain we show that we can develop ANNs with separate populations of excitatory and inhibitory units that learn just as well as standard ANNs. We call these networks Dale's ANNs (DANNs). We present two insights that enable DANNs to learn well: (1) DANNs are related to normalization schemes, and can be initialized such that the inhibition centres and standardizes the excitatory activity, (2) updates to inhibitory neuron parameters should be scaled using corrections based on the Fisher Information matrix. These results demonstrate how ANNs that respect Dale's principle can be built without sacrificing learning performance, which is important for future work using ANNs as models of the brain. The results may also have interesting implications for how inhibitory plasticity in the real brain operates.
Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie LIU, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, Ming Zhou
Pre-trained models for programming language have achieved dramatic empirical improvements on a variety of code-related tasks such as code search, code completion, code summarization, etc. However, existing pre-trained models regard a code snippet as a sequence of tokens, while ignoring the inherent structure of code, which provides crucial code semantics and would enhance the code understanding process. We present GraphCodeBERT, a pre-trained model for programming language that considers the inherent structure of code. Instead of taking syntactic-level structure of code like abstract syntax tree (AST), we use data flow in the pre-training stage, which is a semantic-level structure of code that encodes the relation of "where-the-value-comes-from" between variables. Such a semantic-level structure is neat and does not bring an unnecessarily deep hierarchy of AST, the property of which makes the model more efficient. We develop GraphCodeBERT based on Transformer. In addition to using the task of masked language modeling, we introduce two structure-aware pre-training tasks. One is to predict code structure edges, and the other is to align representations between source code and code structure. We implement the model in an efficient way with a graph-guided masked attention function to incorporate the code structure. We evaluate our model on four tasks, including code search, clone detection, code translation, and code refinement. Results show that code structure and newly introduced pre-training tasks can improve GraphCodeBERT and achieves state-of-the-art performance on the four downstream tasks. We further show that the model prefers structure-level attentions over token-level attentions in the task of code search.
Valerie Chen, Abhinav Gupta, Kenneth Marino
Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To facilitate the automatic decomposition of hierarchical tasks, we propose the use of step-by-step human demonstrations in the form of natural language instructions and action trajectories. We introduce a dataset of such demonstrations in a crafting-based grid world. Our model consists of a high-level language generator and low-level policy, conditioned on language. We find that human demonstrations help solve the most complex tasks. We also find that incorporating natural language allows the model to generalize to unseen tasks in a zero-shot setting and to learn quickly from a few demonstrations. Generalization is not only reflected in the actions of the agent, but also in the generated natural language instructions in unseen tasks. Our approach also gives our trained agent interpretable behaviors because it is able to generate a sequence of high-level descriptions of its actions.
Dihan Zheng, Sia Huat Tan, Xiaowen Zhang, Zuoqiang Shi, Kaisheng Ma, Chenglong Bao
tl;dr: We propose an unsupervised real-world image denoising approach that combines DNNs with classical MAP approaches.
Designing an unsupervised image denoising approach in practical applications is a challenging task due to the complicated data acquisition process. In the real-world case, the noise distribution is so complex that the simplified additive white Gaussian (AWGN) assumption rarely holds, which significantly deteriorates the Gaussian denoisers' performance. To address this problem, we apply a deep neural network that maps the noisy image into a latent space in which the AWGN assumption holds, and thus any existing Gaussian denoiser is applicable. More specifically, the proposed neural network consists of the encoder-decoder structure and approximates the likelihood term in the Bayesian framework. Together with a Gaussian denoiser, the neural network can be trained with the input image itself and does not require any pre-training in other datasets. Extensive experiments on real-world noisy image datasets have shown that the combination of neural networks and Gaussian denoisers improves the performance of the original Gaussian denoisers by a large margin. In particular, the neural network+BM3D method significantly outperforms other unsupervised denoising approaches and is competitive with supervised networks such as DnCNN, FFDNet, and CBDNet.
Cheng Wang, Carolin Lawrence, Mathias Niepert
tl;dr: A method to estimate and calibrate uncertainty in recurrent state transitions.
Uncertainty quantification is crucial for building reliable and trustable machine learning systems. We propose to estimate uncertainty in recurrent neural networks (RNNs) via stochastic discrete state transitions over recurrent timesteps. The uncertainty of the model can be quantified by running a prediction several times, each time sampling from the recurrent state transition distribution, leading to potentially different results if the model is uncertain. Alongside uncertainty quantification, our proposed method offers several advantages in different settings. The proposed method can (1) learn deterministic and probabilistic automata from data, (2) learn well-calibrated models on real-world classification tasks, (3) improve the performance of out-of-distribution detection, and (4) control the exploration-exploitation trade-off in reinforcement learning. An implementation is available.
Marton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew Mingbo Dai, Dustin Tran
tl;dr: We show that a deep neural network can be trained to give multiple independent predictions simultaneously, which results in a computationally efficient ensemble model.
Recent approaches to efficiently ensemble neural networks have shown that strong robustness and uncertainty performance can be achieved with a negligible gain in parameters over the original network. However, these methods still require multiple forward passes for prediction, leading to a significant runtime cost. In this work, we show a surprising result: the benefits of using multiple predictions can be achieved 'for free' under a single model's forward pass. In particular, we show that, using a multi-input multi-output (MIMO) configuration, one can utilize a single model's capacity to train multiple subnetworks that independently learn the task at hand. By ensembling the predictions made by the subnetworks, we improve model robustness without increasing compute. We observe a significant improvement in negative log-likelihood, accuracy, and calibration error on CIFAR10, CIFAR100, ImageNet, and their out-of-distribution variants compared to previous methods.
Xin Wang, Jie Ren, Shuyun Lin, Xiangming Zhu, Yisen Wang, Quanshi Zhang
tl;dr: We prove the close relationship between the interaction and adversarial transferability, provide a unified explanation for previous transferability-boosting methods, and develop a loss to improve adversarial transferability.
In this paper, we use the interaction inside adversarial perturbations to explain and boost the adversarial transferability. We discover and prove the negative correlation between the adversarial transferability and the interaction inside adversarial perturbations. The negative correlation is further verified through different DNNs with various inputs. Moreover, this negative correlation can be regarded as a unified perspective to understand current transferability-boosting methods. To this end, we prove that some classic methods of enhancing the transferability essentially decease interactions inside adversarial perturbations. Based on this, we propose to directly penalize interactions during the attacking process, which significantly improves the adversarial transferability. We will release the code when the paper is accepted.
Oliver Cobb, Christopher G. R. Wallis, Augustine N. Mavor-Parker, Augustin Marignier, Matthew A. Price, Mayeul d'Avezac, Jason McEwen
Many problems across computer vision and the natural sciences require the analysis of spherical data, for which representations may be learned efficiently by encoding equivariance to rotational symmetries. We present a generalized spherical CNN framework that encompasses various existing approaches and allows them to be leveraged alongside each other. The only existing non-linear spherical CNN layer that is strictly equivariant has complexity $\mathcal{O}(C^2L^5)$, where $C$ is a measure of representational capacity and $L$ the spherical harmonic bandlimit. Such a high computational cost often prohibits the use of strictly equivariant spherical CNNs. We develop two new strictly equivariant layers with reduced complexity $\mathcal{O}(CL^4)$ and $\mathcal{O}(CL^3 \log L)$, making larger, more expressive models computationally feasible. Moreover, we adopt efficient sampling theory to achieve further computational savings. We show that these developments allow the construction of more expressive hybrid models that achieve state-of-the-art accuracy and parameter efficiency on spherical benchmark problems.
Carl Allen, Ivana Balazevic, Timothy Hospedales
tl;dr: Interpreting the structure of knowledge graph relation representation using insight from word embeddings.
Many models learn representations of knowledge graph data by exploiting its low-rank latent structure, encoding known relations between entities and enabling unknown facts to be inferred. To predict whether a relation holds between entities, embeddings are typically compared in the latent space following a relation-specific mapping. Whilst their predictive performance has steadily improved, how such models capture the underlying latent structure of semantic information remains unexplained. Building on recent theoretical understanding of word embeddings, we categorise knowledge graph relations into three types and for each derive explicit requirements of their representations. We show that empirical properties of relation representations and the relative performance of leading knowledge graph representation methods are justified by our analysis.
John Zarka, Florentin Guth, Stéphane Mallat
Numerical experiments demonstrate that deep neural network classifiers progressively separate class distributions around their mean, achieving linear separability on the training set, and increasing the Fisher discriminant ratio. We explain this mechanism with two types of operators. We prove that a rectifier without biases applied to sign-invariant tight frames can separate class means and increase Fisher ratios. On the opposite, a soft-thresholding on tight frames can reduce within-class variabilities while preserving class means. Variance reduction bounds are proved for Gaussian mixture models. For image classification, we show that separation of class means can be achieved with rectified wavelet tight frames that are not learned. It defines a scattering transform. Learning $1 \times 1$ convolutional tight frames along scattering channels and applying a soft-thresholding reduces within-class variabilities. The resulting scattering network reaches the classification accuracy of ResNet-18 on CIFAR-10 and ImageNet, with fewer layers and no learned biases.
Abhishek Sinha, Kumar Ayush, Jiaming Song, Burak Uzkent, Hongxia Jin, Stefano Ermon
tl;dr: We propose a framework to do Negative Data Augmentation for generative models and self-supervised learning
Data augmentation is often used to enlarge datasets with synthetic samples generated in accordance with the underlying data distribution. To enable a wider range of augmentations, we explore negative data augmentation strategies (NDA) that intentionally create out-of-distribution samples. We show that such negative out-of-distribution samples provide information on the support of the data distribution, and can be leveraged for generative modeling and representation learning. We introduce a new GAN training objective where we use NDA as an additional source of synthetic data for the discriminator. We prove that under suitable conditions, optimizing the resulting objective still recovers the true data distribution but can directly bias the generator towards avoiding samples that lack the desired structure. Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities. Further, we incorporate the same negative data augmentation strategy in a contrastive learning framework for self-supervised representation learning on images and videos, achieving improved performance on downstream image classification, object detection, and action recognition tasks. These results suggest that prior knowledge on what does not constitute valid data is an effective form of weak supervision across a range of unsupervised learning tasks.
Guolin Ke, Di He, Tie-Yan Liu
tl;dr: A novel and better positional encoding method for Transformer-based language pre-training models.
In this work, we investigate the positional encoding methods used in language pre-training (e.g., BERT) and identify several problems in the existing formulations. First, we show that in the absolute positional encoding, the addition operation applied on positional embeddings and word embeddings brings mixed correlations between the two heterogeneous information resources. It may bring unnecessary randomness in the attention and further limit the expressiveness of the model. Second, we question whether treating the position of the symbol \texttt{[CLS]} the same as other words is a reasonable design, considering its special role (the representation of the entire sentence) in the downstream tasks. Motivated from above analysis, we propose a new positional encoding method called \textbf{T}ransformer with \textbf{U}ntied \textbf{P}ositional \textbf{E}ncoding (TUPE). In the self-attention module, TUPE computes the word contextual correlation and positional correlation separately with different parameterizations and then adds them together. This design removes the mixed and noisy correlations over heterogeneous embeddings and offers more expressiveness by using different projection matrices. Furthermore, TUPE unties the \texttt{[CLS]} symbol from other positions, making it easier to capture information from all positions. Extensive experiments and ablation studies on GLUE benchmark demonstrate the effectiveness of the proposed method. Codes and models are released at \url{}.
Dan A. Calian, Daniel J Mankowitz, Tom Zahavy, Zhongwen Xu, Junhyuk Oh, Nir Levine, Timothy Mann
tl;dr: This paper uses meta-gradients to perform soft-constrained Reinforcement Learning (RL) optimization
Deploying Reinforcement Learning (RL) agents to solve real-world applications often requires satisfying complex system constraints. Often the constraint thresholds are incorrectly set due to the complex nature of a system or the inability to verify the thresholds offline (e.g, no simulator or reasonable offline evaluation procedure exists). This results in solutions where a task cannot be solved without violating the constraints. However, in many real-world cases, constraint violations are undesirable yet they are not catastrophic, motivating the need for soft-constrained RL approaches. We present two soft-constrained RL approaches that utilize meta-gradients to find a good trade-off between expected return and minimizing constraint violations. We demonstrate the effectiveness of these approaches by showing that they consistently outperform the baselines across four different Mujoco domains.
eran malach, Shai Shalev-Shwartz
tl;dr: We show a computational separation between convolutional and fully-connected networks, proving that the former can leverage strong local structure in the data.
Convolutional neural networks (CNN) exhibit unmatched performance in a multitude of computer vision tasks. However, the advantage of using convolutional networks over fully-connected networks is not understood from a theoretical perspective. In this work, we show how convolutional networks can leverage locality in the data, and thus achieve a computational advantage over fully-connected networks. Specifically, we show a class of problems that can be efficiently solved using convolutional networks trained with gradient-descent, but at the same time is hard to learn using a polynomial-size fully-connected network.
Tao Zhuo, Mohan Kankanhalli
tl;dr: We propose a simple yet effective Dual-Contrast Network (DCNet) to solve Raven's progressive matrices without using auxiliary annotations and assumptions.
As a step towards improving the abstract reasoning capability of machines, we aim to solve Raven’s Progressive Matrices (RPM) with neural networks, since solving RPM puzzles is highly correlated with human intelligence. Unlike previous methods that use auxiliary annotations or assume hidden rules to produce appropriate feature representation, we only use the ground truth answer of each question for model learning, aiming for an intelligent agent to have a strong learning capability with a small amount of supervision. Based on the RPM problem formulation, the correct answer filled into the missing entry of the third row/column has to best satisfy the same rules shared between the first two rows/columns.Thus we design a simple yet effective Dual-Contrast Network (DCNet) to exploit the inherent structure of RPM puzzles. Specifically, a rule contrast module is designed to compare the latent rules between the filled row/column and the first two rows/columns; a choice contrast module is designed to increase the relative differences between candidate choices. Experimental results on the RAVEN and PGM datasets show that DCNet outperforms the state-of-the-art methods by a large margin of 5.77%. Further experiments on few training samples and model generalization also show the effectiveness of DCNet. Code is available at
Edoardo Cetin, Oya Celiktutan
tl;dr: Imitation of visual expert demonstrations robust to appearance and embodiment mismatch, working for high dimensional control problems.
Human beings are able to understand objectives and learn by simply observing others perform a task. Imitation learning methods aim to replicate such capabilities, however, they generally depend on access to a full set of optimal states and actions taken with the agent's actuators and from the agent's point of view. In this paper, we introduce a new algorithm - called Disentangling Generative Adversarial Imitation Learning (DisentanGAIL) - with the purpose of bypassing such constraints. Our algorithm enables autonomous agents to learn directly from high dimensional observations of an expert performing a task, by making use of adversarial learning with a latent representation inside the discriminator network. Such latent representation is regularized through mutual information constraints to incentivize learning only features that encode information about the completion levels of the task being demonstrated. This allows to obtain a shared feature space to successfully perform imitation while disregarding the differences between the expert's and the agent's domains. Empirically, our algorithm is able to efficiently imitate in a diverse range of control problems including balancing, manipulation and locomotive tasks, while being robust to various domain differences in terms of both environment appearance and agent embodiment.
Zixiang Chen, Yuan Cao, Difan Zou, Quanquan Gu
tl;dr: We establish learning guarantees for deep ReLU networks with width polylogarithmic in sample size and the inverse of the target error.
A recent line of research on deep learning focuses on the extremely over-parameterized setting, and shows that when the network width is larger than a high degree polynomial of the training sample size $n$ and the inverse of the target error $\epsilon^{-1}$, deep neural networks learned by (stochastic) gradient descent enjoy nice optimization and generalization guarantees. Very recently, it is shown that under certain margin assumptions on the training data, a polylogarithmic width condition suffices for two-layer ReLU networks to converge and generalize (Ji and Telgarsky, 2020). However, whether deep neural networks can be learned with such a mild over-parameterization is still an open question. In this work, we answer this question affirmatively and establish sharper learning guarantees for deep ReLU networks trained by (stochastic) gradient descent. In specific, under certain assumptions made in previous work, our optimization and generalization guarantees hold with network width polylogarithmic in $n$ and $\epsilon^{-1}$. Our results push the study of over-parameterized deep neural networks towards more practical settings.
Javier Antoran, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández-Lobato
tl;dr: We introduce a method to help explain uncertainties of any differentiable probabilistic model by perturbing input features.
Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems. However, there is little work at the intersection of these two areas. We address this gap by proposing a novel method for interpreting uncertainty estimates from differentiable probabilistic models, like Bayesian Neural Networks (BNNs). Our method, Counterfactual Latent Uncertainty Explanations (CLUE), indicates how to change an input, while keeping it on the data manifold, such that a BNN becomes more confident about the input's prediction. We validate CLUE through 1) a novel framework for evaluating counterfactual explanations of uncertainty, 2) a series of ablation experiments, and 3) a user study. Our experiments show that CLUE outperforms baselines and enables practitioners to better understand which input patterns are responsible for predictive uncertainty.
Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models. We draw a connection between such autoregressive generative models and the task of lossy video compression. Specifically, we view recent neural video compression methods (Lu et al., 2019; Yang et al., 2020b; Agustssonet al., 2020) as instances of a generalized stochastic temporal autoregressive transform, and propose avenues for enhancement based on this insight. Comprehensive evaluations on large-scale video data show improved rate-distortion performance over both state-of-the-art neural and conventional video compression methods.
Xiaobo Xia, Tongliang Liu, Bo Han, Chen Gong, Nannan Wang, Zongyuan Ge, Yi Chang
The \textit{memorization effects} of deep networks show that they will first memorize training data with clean labels and then those with noisy labels. The \textit{early stopping} method therefore can be exploited for learning with noisy labels. However, the side effect brought by noisy labels will influence the memorization of clean labels before early stopping. In this paper, motivated by the \textit{lottery ticket hypothesis} which shows that only partial parameters are important for generalization, we find that only partial parameters are important for fitting clean labels and generalize well, which we term as \textit{critical parameters}; while the other parameters tend to fit noisy labels and cannot generalize well, which we term as \textit{non-critical parameters}. Based on this, we propose \textit{robust early-learning} to reduce the side effect of noisy labels before early stopping and thus enhance the memorization of clean labels. Specifically, in each iteration, we divide all parameters into the critical and non-critical ones, and then perform different update rules for different types of parameters. Extensive experiments on benchmark-simulated and real-world label-noise datasets demonstrate the superiority of the proposed method over the state-of-the-art label-noise learning methods.
Alexandre Rame, Matthieu Cord
tl;dr: Driven by arguments from information theory, we introduce a new learning strategy for deep ensembles that increases diversity among members: we adversarially prevent features from being conditionally redundant, i.e., predictable from each other.
Deep ensembles perform better than a single network thanks to the diversity among their members. Recent approaches regularize predictions to increase diversity; however, they also drastically decrease individual members’ performances. In this paper, we argue that learning strategies for deep ensembles need to tackle the trade-off between ensemble diversity and individual accuracies. Motivated by arguments from information theory and leveraging recent advances in neural estimation of conditional mutual information, we introduce a novel training criterion called DICE: it increases diversity by reducing spurious correlations among features. The main idea is that features extracted from pairs of members should only share information useful for target class prediction without being conditionally redundant. Therefore, besides the classification loss with information bottleneck, we adversarially prevent features from being conditionally predictable from each other. We manage to reduce simultaneous errors while protecting class information. We obtain state-of-the-art accuracy results on CIFAR-10/100: for example, an ensemble of 5 networks trained with DICE matches an ensemble of 7 networks trained independently. We further analyze the consequences on calibration, uncertainty estimation, out-of-distribution detection and online co-distillation.
Minjia Zhang, Menghao Li, Chi Wang, Mingqin Li
tl;dr: We accelerate tensor program optimization by considering it as a multi-armed bandits problem and using Bayesian inference to achieve fast convergence.
Recently, the DL compiler, together with Learning to Compile has proven to be a powerful technique for optimizing deep learning models. However, existing methods focus on accelerating the convergence speed of the individual tensor operator rather than the convergence speed of the entire model, which results in long optimization time to obtain a desired latency. In this paper, we present a new method called DynaTune, which provides significantly faster convergence speed to optimize a DNN model. In particular, we consider a Multi-Armed Bandit (MAB) model for the tensor program optimization problem. We use UCB to handle the decision-making of time-slot-based optimization, and we devise a Bayesian belief model that allows predicting the potential performance gain of each operator with uncertainty quantification, which guides the optimization process. We evaluate and compare DynaTune with the state-of-the-art DL compiler. The experiment results show that DynaTune is 1.2--2.4 times faster to achieve the same optimization quality for a range of models across different hardware architectures.
Phillip Lippe, Efstratios Gavves
tl;dr: We explore the application of normalizing flows on categorical data and propose a permutation-invariant generative model on graphs, called GraphCNF.
Despite their popularity, to date, the application of normalizing flows on categorical data stays limited. The current practice of using dequantization to map discrete data to a continuous space is inapplicable as categorical data has no intrinsic order. Instead, categorical data have complex and latent relations that must be inferred, like the synonymy between words. In this paper, we investigate Categorical Normalizing Flows, that is normalizing flows for categorical data. By casting the encoding of categorical data in continuous space as a variational inference problem, we jointly optimize the continuous representation and the model likelihood. Using a factorized decoder, we introduce an inductive bias to model any interactions in the normalizing flow. As a consequence, we do not only simplify the optimization compared to having a joint decoder, but also make it possible to scale up to a large number of categories that is currently impossible with discrete normalizing flows. Based on Categorical Normalizing Flows, we propose GraphCNF a permutation-invariant generative model on graphs. GraphCNF implements a three step approach modeling the nodes, edges, and adjacency matrix stepwise to increase efficiency. On molecule generation, GraphCNF outperforms both one-shot and autoregressive flow-based state-of-the-art.
Gautier Izacard, Edouard Grave
tl;dr: We show that attention scores obtained by training a model to answer questions given a set of support documents can be used to train a model to select relevant passages in a knowledge source.
The task of information retrieval is an important component of many natural language processing systems, such as open domain question answering. While traditional methods were based on hand-crafted features, continuous representations based on neural networks recently obtained competitive results. A challenge of using such methods is to obtain supervised data to train the retriever model, corresponding to pairs of query and support documents. In this paper, we propose a technique to learn retriever models for downstream tasks, inspired by knowledge distillation, and which does not require annotated pairs of query and documents. Our approach leverages attention scores of a reader model, used to solve the task based on retrieved documents, to obtain synthetic labels for the retriever. We evaluate our method on question answering, obtaining state-of-the-art results.
Jiayi Shen, Xiaohan Chen, Howard Heaton, Tianlong Chen, Jialin Liu, Wotao Yin, Zhangyang Wang
tl;dr: This paper introduces the learning to optimize (L2O) methodology, called Twin L2O, for minimax optimization consisting of two LSTMs.
Solving continuous minimax optimization is of extensive practical interest, yet notoriously unstable and difficult. This paper introduces the learning to optimize(L2O) methodology to the minimax problems for the first time and addresses its accompanying unique challenges. We first present Twin-L2O, the first dedicated minimax L2O method consisting of two LSTMs for updating min and max variables separately. The decoupled design is found to facilitate learning, particularly when the min and max variables are highly asymmetric. Empirical experiments on a variety of minimax problems corroborate the effectiveness of Twin-L2O. We then discuss a crucial concern of Twin-L2O, i.e., its inevitably limited generalizability to unseen optimizees. To address this issue, we present two complementary strategies. Our first solution, Enhanced Twin-L2O, is empirically applicable for general minimax problems, by improving L2O training via leveraging curriculum learning. Our second alternative, called Safeguarded Twin-L2O, is a preliminary theoretical exploration stating that under some strong assumptions, it is possible to theoretically establish the convergence of Twin-L2O. We benchmark our algorithms on several testbed problems and compare against state-of-the-art minimax solvers. The code is available at:
Maxwell Nye, Yewen Pu, Matthew Bowers, Jacob Andreas, Joshua B. Tenenbaum, Armando Solar-Lezama
tl;dr: We use a combination of concrete execution and learned neural semantics to represent partial programs, resulting in more accurate program synthesis.
Synthesizing programs from examples requires searching over a vast, combinatorial space of possible programs. In this search process, a key challenge is representing the behavior of a partially written program before it can be executed, to judge if it is on the right track and predict where to search next. We introduce a general technique for representing partially written programs in a program synthesis engine. We take inspiration from the technique of abstract interpretation, in which an approximate execution model is used to determine if an unfinished program will eventually satisfy a goal specification. Here we learn an approximate execution model implemented as a modular neural network. By constructing compositional program representations that implicitly encode the interpretation semantics of the underlying programming language, we can represent partial programs using a flexible combination of concrete execution state and learned neural representations, using the learned approximate semantics when concrete semantics are not known (in unfinished parts of the program). We show that these hybrid neuro-symbolic representations enable execution-guided synthesizers to use more powerful language constructs, such as loops and higher-order functions, and can be used to synthesize programs more accurately for a given search budget than pure neural approaches in several domains.
Juntang Zhuang, Nicha C Dvornek, sekhar tatikonda, James s Duncan
tl;dr: A solver for ODE that guarantees accuracy in reverse-time trajectory at a constant memory cost
Neural ordinary differential equations (Neural ODEs) are a new family of deep-learning models with continuous depth. However, the numerical estimation of the gradient in the continuous case is not well solved: existing implementations of the adjoint method suffer from inaccuracy in reverse-time trajectory, while the naive method and the adaptive checkpoint adjoint method (ACA) have a memory cost that grows with integration time. In this project, based on the asynchronous leapfrog (ALF) solver, we propose the Memory-efficient ALF Integrator (MALI), which has a constant memory cost $w.r.t$ integration time similar to the adjoint method, and guarantees accuracy in reverse-time trajectory (hence accuracy in gradient estimation). We validate MALI in various tasks: on image recognition tasks, to our knowledge, MALI is the first to enable feasible training of a Neural ODE on ImageNet and outperform a well-tuned ResNet, while existing methods fail due to either heavy memory burden or inaccuracy; for time series modeling, MALI significantly outperforms the adjoint method; and for continuous generative models, MALI achieves new state-of-the-art performance. We provide a pypi package:
Pablo Morales-Alvarez, Daniel Hernández-Lobato, Rafael Molina, José Miguel Hernández-Lobato
tl;dr: We use 1D Gaussian Processes to introduce activation-level uncertainty in neural networks, which overcomes known limitations of (functional) Bayesian neural nets and obtains better results than the related deep Gaussian Processes.
Current approaches for uncertainty estimation in deep learning often produce too confident results. Bayesian Neural Networks (BNNs) model uncertainty in the space of weights, which is usually high-dimensional and limits the quality of variational approximations. The more recent functional BNNs (fBNNs) address this only partially because, although the prior is specified in the space of functions, the posterior approximation is still defined in terms of stochastic weights. In this work we propose to move uncertainty from the weights (which are deterministic) to the activation function. Specifically, the activations are modelled with simple 1D Gaussian Processes (GP), for which a triangular kernel inspired by the ReLu non-linearity is explored. Our experiments show that activation-level stochasticity provides more reliable uncertainty estimates than BNN and fBNN, whereas it performs competitively in standard prediction tasks. We also study the connection with deep GPs, both theoretically and empirically. More precisely, we show that activation-level uncertainty requires fewer inducing points and is better suited for deep architectures.
Yuanyuan Yuan, Shuai Wang, Junping Zhang
tl;dr: We present the first generative model-based side channel analysis (SCA) to reconstruct private user images.
System side channels denote effects imposed on the underlying system and hardware when running a program, such as its accessed CPU cache lines. Side channel analysis (SCA) allows attackers to infer program secrets based on observed side channel signals. Given the ever-growing adoption of machine learning as a service (MLaaS), image analysis software on cloud platforms has been exploited by reconstructing private user images from system side channels. Nevertheless, to date, SCA is still highly challenging, requiring technical knowledge of victim software's internal operations. For existing SCA attacks, comprehending such internal operations requires heavyweight program analysis or manual efforts. This research proposes an attack framework to reconstruct private user images processed by media software via system side channels. The framework forms an effective workflow by incorporating convolutional networks, variational autoencoders, and generative adversarial networks. Our evaluation of two popular side channels shows that the reconstructed images consistently match user inputs, making privacy leakage attacks more practical. We also show surprising results that even one-bit data read/write pattern side channels, which are deemed minimally informative, can be used to reconstruct quality images using our framework.
Nanxuan Zhao, Zhirong Wu, Rynson W. H. Lau, Stephen Lin
tl;dr: Understanding why self-supervised contrastive learning outperforms supervised counterparts for image pretraining
Contrastive visual pretraining based on the instance discrimination pretext task has made significant progress. Notably, recent work on unsupervised pretraining has shown to surpass the supervised counterpart for finetuning downstream applications such as object detection and segmentation. It comes as a surprise that image annotations would be better left unused for transfer learning. In this work, we investigate the following problems: What makes instance discrimination pretraining good for transfer learning? What knowledge is actually learned and transferred from these models? From this understanding of instance discrimination, how can we better exploit human annotation labels for pretraining? Our findings are threefold. First, what truly matters for the transfer is low-level and mid-level representations, not high-level representations. Second, the intra-category invariance enforced by the traditional supervised model weakens transferability by increasing task misalignment. Finally, supervised pretraining can be strengthened by following an exemplar-based approach without explicit constraints among the instances within the same category.
Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang, Han Zhao, Louis-Philippe Morency, Ruslan Salakhutdinov
tl;dr: We present RPC, the Relative Predictive Coding, that achieves a good balance among the three challenges when modeling a contrastive learning objective: training stability, sensitivity to minibatch size, and downstream task performance.
This paper introduces Relative Predictive Coding (RPC), a new contrastive representation learning objective that maintains a good balance among training stability, minibatch size sensitivity, and downstream task performance. The key to the success of RPC is two-fold. First, RPC introduces the relative parameters to regularize the objective for boundedness and low variance. Second, RPC contains no logarithm and exponential score functions, which are the main cause of training instability in prior contrastive objectives. We empirically verify the effectiveness of RPC on benchmark vision and speech self-supervised learning tasks. Lastly, we relate RPC with mutual information (MI) estimation, showing RPC can be used to estimate MI with low variance.
Jiahui Yu, Wei Han, Anmol Gulati, Chung-Cheng Chiu, Bo Li, Tara N Sainath, Yonghui Wu, Ruoming Pang
tl;dr: Dual-mode ASR unifies and improves Streaming ASR with full-context modeling, simplifying the development and deployment workflow and improving both latency and accuracy.
Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this work, we propose a unified framework, Dual-mode ASR, to train a single end-to-end ASR model with shared weights for both streaming and full-context speech recognition. We show that the latency and accuracy of streaming ASR significantly benefit from weight sharing and joint training of full-context ASR, especially with inplace knowledge distillation during the training. The Dual-mode ASR framework can be applied to recent state-of-the-art convolution-based and transformer-based ASR networks. We present extensive experiments with two state-of-the-art ASR networks, ContextNet and Conformer, on two datasets, a widely used public dataset LibriSpeech and a large-scale dataset MultiDomain. Experiments and ablation studies demonstrate that Dual-mode ASR not only simplifies the workflow of training and deploying streaming and full-context ASR models, but also significantly improves both emission latency and recognition accuracy of streaming ASR. With Dual-mode ASR, we achieve new state-of-the-art streaming ASR results on both LibriSpeech and MultiDomain in terms of accuracy and latency.
Zhuotong Chen, Qianxiao Li, Zheng Zhang
tl;dr: We propose a close-loop control framework to improve the robustness of neural networks under various data perturbations.
Despite their success in massive engineering applications, deep neural networks are vulnerable to various perturbations due to their black-box nature. Recent study has shown that a deep neural network can misclassify the data even if the input data is perturbed by an imperceptible amount. In this paper, we address the robustness issue of neural networks by a novel close-loop control method from the perspective of dynamic systems. Instead of modifying the parameters in a fixed neural network architecture, a close-loop control process is added to generate control signals adaptively for the perturbed or corrupted data. We connect the robustness of neural networks with optimal control using the geometrical information of underlying data to design the control objective. The detailed analysis shows how the embedding manifolds of state trajectory affect error estimation of the proposed method. Our approach can simultaneously maintain the performance on clean data and improve the robustness against many types of data perturbations. It can also further improve the performance of robustly trained neural networks against different perturbations. To the best of our knowledge, this is the first work that improves the robustness of neural networks with close-loop control.
Jiaojiao Zhao, Cees G. M. Snoek
Pooling is a critical operation in convolutional neural networks for increasing receptive fields and improving robustness to input variations. Most existing pooling operations downsample the feature maps, which is a lossy process. Moreover, they are not invertible: upsampling a downscaled feature map can not recover the lost information in the downsampling. By adopting the philosophy of the classical Lifting Scheme from signal processing, we propose LiftPool for bidirectional pooling layers, including LiftDownPool and LiftUpPool. LiftDownPool decomposes a feature map into various downsized sub-bands, each of which contains information with different frequencies. As the pooling function in LiftDownPool is perfectly invertible, by performing LiftDownPool backward, a corresponding up-pooling layer LiftUpPool is able to generate a refined upsampled feature map using the detail subbands, which is useful for image-to-image translation challenges. Experiments show the proposed methods achieve better results on image classification and semantic segmentation, using various backbones. Moreover, LiftDownPool offers better robustness to input corruptions and perturbations.
Simon Shaolei Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei
tl;dr: We study when and how much representation learning can help few-shot learning by drastically reducing sample complexity on the target task.
This paper studies few-shot learning via representation learning, where one uses $T$ source tasks with $n_1$ data per task to learn a representation in order to reduce the sample complexity of a target task for which there is only $n_2 (\ll n_1)$ data. Specifically, we focus on the setting where there exists a good common representation between source and target, and our goal is to understand how much a sample size reduction is possible. First, we study the setting where this common representation is low-dimensional and provide a risk bound of $\tilde{O}(\frac{dk}{n_1T} + \frac{k}{n_2})$ on the target task for the linear representation class; here $d$ is the ambient input dimension and $k (\ll d)$ is the dimension of the representation. This result bypasses the $\Omega(\frac{1}{T})$ barrier under the i.i.d. task assumption, and can capture the desired property that all $n_1T$ samples from source tasks can be \emph{pooled} together for representation learning. We further extend this result to handle a general representation function class and obtain a similar result. Next, we consider the setting where the common representation may be high-dimensional but is capacity-constrained (say in norm); here, we again demonstrate the advantage of representation learning in both high-dimensional linear regression and neural networks, and show that representation learning can fully utilize all $n_1T$ samples from source tasks.
Zhiyuan Li, Yuping Luo, Kaifeng Lyu
tl;dr: We prove that for depth-2 matrix factorization, gradient flow with infinitesimal initialization is mathematically equivalent to a simple heuristic rank minimization algorithm, Greedy Low-Rank Learning, under some reasonable assumptions.
Matrix factorization is a simple and natural test-bed to investigate the implicit regularization of gradient descent. Gunasekar et al. (2017) conjectured that gradient flow with infinitesimal initialization converges to the solution that minimizes the nuclear norm, but a series of recent papers argued that the language of norm minimization is not sufficient to give a full characterization for the implicit regularization. In this work, we provide theoretical and empirical evidence that for depth-2 matrix factorization, gradient flow with infinitesimal initialization is mathematically equivalent to a simple heuristic rank minimization algorithm, Greedy Low-Rank Learning, under some reasonable assumptions. This generalizes the rank minimization view from previous works to a much broader setting and enables us to construct counter-examples to refute the conjecture from Gunasekar et al. (2017). We also extend the results to the case where depth >= 3, and we show that the benefit of being deeper is that the above convergence has a much weaker dependence over initialization magnitude so that this rank minimization is more likely to take effect for initialization with practical scale.
Wangchunshu Zhou, Dong-Ho Lee, Ravi Kiran Selvam, Seyeon Lee, Xiang Ren
tl;dr: We propose self-supervised objectives and a joint training framework to augment pre-trained language models with common sense without relying on external knowledge bases.
Pretrained language models (PTLM) have achieved impressive results in a range of natural language understanding (NLU) and generation (NLG) tasks that require a syntactic and semantic understanding of the text. However, current pre-training objectives such as masked token prediction (for BERT-style PTLMs) and masked span infilling (for T5-style PTLMs) do not explicitly model the relational and compositional commonsense knowledge about everyday concepts, which is crucial to many downstream tasks requiring commonsense reasoning. To augment PTLMs with common sense, we propose generative and contrastive objectives as intermediate self-supervised pre-training tasks between general pre-training and downstream task-specific fine-tuning. We also propose a joint training framework to unify generative and contrastive objectives so that these objectives can be more effective. Our proposed objectives can pack more commonsense knowledge into the parameters of a pre-trained text-to-text transformer without relying on external knowledge bases, yielding better performance on both NLU and NLG tasks. We apply our method on a pre-trained T5 model in an intermediate task transfer learning fashion to train a concept-aware language model (CALM) and experiment with five commonsense benchmarks (four NLU tasks and one NLG task). Experimental results show that CALM outperforms baseline methods by a consistent margin.
Benjamin Eysenbach, Shreyas Chaudhari, Swapnil Asawa, Sergey Levine, Ruslan Salakhutdinov
tl;dr: We propose a method for addressing domain adaptation in RL by using a (learned) modified reward, and prove that our method recovers a near-optimal policy for the target domain.
We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. Our approach stems from the idea that the agent's experience in the source domain should look similar to its experience in the target domain. Building off of a probabilistic view of RL, we achieve this goal by compensating for the difference in dynamics by modifying the reward function. This modified reward function is simple to estimate by learning auxiliary classifiers that distinguish source-domain transitions from target-domain transitions. Intuitively, the agent is penalized for transitions that would indicate that the agent is interacting with the source domain, rather than the target domain. Formally, we prove that applying our method in the source domain is guaranteed to obtain a near-optimal policy for the target domain, provided that the source and target domains satisfy a lightweight assumption. Our approach is applicable to domains with continuous states and actions and does not require learning an explicit model of the dynamics. On discrete and continuous control tasks, we illustrate the mechanics of our approach and demonstrate its scalability to high-dimensional~tasks.
Zhuang Liu, Xuanlin Li, Bingyi Kang, Trevor Darrell
tl;dr: We show that conventional regularization methods (e.g., $L_2$), which have been largely ignored in RL methods, can be very effective in policy optimization on continuous control tasks; we also analyze why they can help from several perspectives.
Deep Reinforcement Learning (Deep RL) has been receiving increasingly more attention thanks to its encouraging performance on a variety of control tasks. Yet, conventional regularization techniques in training neural networks (e.g., $L_2$ regularization, dropout) have been largely ignored in RL methods, possibly because agents are typically trained and evaluated in the same environment, and because the deep RL community focuses more on high-level algorithm designs. In this work, we present the first comprehensive study of regularization techniques with multiple policy optimization algorithms on continuous control tasks. Interestingly, we find conventional regularization techniques on the policy networks can often bring large improvement, especially on harder tasks. Our findings are shown to be robust against training hyperparameter variations. We also compare these techniques with the more widely used entropy regularization. In addition, we study regularizing different components and find that only regularizing the policy network is typically the best. We further analyze why regularization may help generalization in RL from four perspectives - sample complexity, reward distribution, weight norm, and noise robustness. We hope our study provides guidance for future practices in regularizing policy optimization algorithms. Our code is available at .
Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani, Casper Kaae Sønderby, Tim Salimans
tl;dr: We analyze and improve integer discrete normalizing flows for lossless source compression.
In this paper we analyse and improve integer discrete flows for lossless compression. Integer discrete flows are a recently proposed class of models that learn invertible transformations for integer-valued random variables. Their discrete nature makes them particularly suitable for lossless compression with entropy coding schemes. We start by investigating a recent theoretical claim that states that invertible flows for discrete random variables are less flexible than their continuous counterparts. We demonstrate with a proof that this claim does not hold for integer discrete flows due to the embedding of data with finite support into the countably infinite integer lattice. Furthermore, we zoom in on the effect of gradient bias due to the straight-through estimator in integer discrete flows, and demonstrate that its influence is highly dependent on architecture choices and less prominent than previously thought. Finally, we show how different architecture modifications improve the performance of this model class for lossless compression, and that they also enable more efficient compression: a model with half the number of flow layers performs on par with or better than the original integer discrete flow model.
Tatsuya Matsushima, Hiroki Furuta, Yutaka Matsuo, Ofir Nachum, Shixiang Gu
tl;dr: We propose a novel method that achieves both high sample-efficiency in offline RL and "deployment-efficiency" in online RL.
Most reinforcement learning (RL) algorithms assume online access to the environment, in which one may readily interleave updates to the policy with experience collection using that policy. However, in many real-world applications such as health, education, dialogue agents, and robotics, the cost or potential risk of deploying a new data-collection policy is high, to the point that it can become prohibitive to update the data-collection policy more than a few times during learning. With this view, we propose a novel concept of deployment efficiency, measuring the number of distinct data-collection policies that are used during policy learning. We observe that naïvely applying existing model-free offline RL algorithms recursively does not lead to a practical deployment-efficient and sample-efficient algorithm. We propose a novel model-based algorithm, Behavior-Regularized Model-ENsemble (BREMEN), that not only performs better than or comparably as the state-of-the-art dynamic-programming-based and concurrently-proposed model-based offline approaches on existing benchmarks, but can also effectively optimize a policy offline using 10-20 times fewer data than prior works. Furthermore, the recursive application of BREMEN achieves impressive deployment efficiency while maintaining the same or better sample efficiency, learning successful policies from scratch on simulated robotic environments with only 5-10 deployments, compared to typical values of hundreds to millions in standard RL baselines.
Siyi Liu, Chen Gao, Yihong Chen, Depeng Jin, Yong Li
tl;dr: Learning flexible feature-aware embedding sizes effectively and efficiently for recommendation models.
The embedding-based representation learning is commonly used in deep learning recommendation models to map the raw sparse features to dense vectors. The traditional embedding manner that assigns a uniform size to all features has two issues. First, the numerous features inevitably lead to a gigantic embedding table that causes a high memory usage cost. Second, it is likely to cause the over-fitting problem for those features that do not require too large representation capacity. Existing works that try to address the problem always cause a significant drop in recommendation performance or suffers from the limitation of unaffordable training time cost. In this paper, we proposed a novel approach, named PEP (short for Plug-in Embedding Pruning), to reduce the size of the embedding table while avoiding the drop of recommendation accuracy. PEP prunes embedding parameter where the pruning threshold(s) can be adaptively learned from data. Therefore we can automatically obtain a mixed-dimension embedding-scheme by pruning redundant parameters for each feature. PEP is a general framework that can plug in various base recommendation models. Extensive experiments demonstrate it can efficiently cut down embedding parameters and boost the base model's performance. Specifically, it achieves strong recommendation performance while reducing 97-99% parameters. As for the computation cost, PEP only brings an additional 20-30% time cost compare with base models.
Marc Anton Finzi, Roberto Bondesan, Max Welling
tl;dr: We build a neural network which integrates internal discretization error and missing values probabilistically with GPs
Continuous input signals like images and time series that are irregularly sampled or have missing values are challenging for existing deep learning methods. Coherently defined feature representations must depend on the values in unobserved regions of the input. Drawing from the work in probabilistic numerics, we propose Probabilistic Numeric Convolutional Neural Networks which represent features as Gaussian processes, providing a probabilistic description of discretization error. We then define a convolutional layer as the evolution of a PDE defined on this GP, followed by a nonlinearity. This approach also naturally admits steerable equivariant convolutions under e.g. the rotation group. In experiments we show that our approach yields a $3\times$ reduction of error from the previous state of the art on the SuperPixel-MNIST dataset and competitive performance on the medical time series dataset PhysioNet2012.
Songwei Ge, Vedanuj Goswami, Larry Zitnick, Devi Parikh
tl;dr: We introduce two creative sketch datasets and DoodlerGAN -- a part-based GAN model that generates creative sketches.
Sketching or doodling is a popular creative activity that people engage in. However, most existing work in automatic sketch understanding or generation has focused on sketches that are quite mundane. In this work, we introduce two datasets of creative sketches -- Creative Birds and Creative Creatures -- containing 10k sketches each along with part annotations. We propose DoodlerGAN -- a part-based Generative Adversarial Network (GAN) -- to generate unseen compositions of novel part appearances. Quantitative evaluations as well as human studies demonstrate that sketches generated by our approach are more creative and of higher quality than existing approaches. In fact, in Creative Birds, subjects prefer sketches generated by DoodlerGAN over those drawn by humans!
David W. Romero, Jean-Baptiste Cordonnier
tl;dr: We provide a general self-attention formulation to impose group equivariance to arbitrary symmetry groups.
We provide a general self-attention formulation to impose group equivariance to arbitrary symmetry groups. This is achieved by defining positional encodings that are invariant to the action of the group considered. Since the group acts on the positional encoding directly, group equivariant self-attention networks (GSA-Nets) are steerable by nature. Our experiments on vision benchmarks demonstrate consistent improvements of GSA-Nets over non-equivariant self-attention networks.
Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu
tl;dr: A new algorithm for differentially private learning that advances state-of-the-art performance on several benchmark datasets. Code:
The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism. However, for meaningful privacy parameters, a differentially private model degrades the utility drastically when the model comprises a large number of trainable parameters. In this paper, we propose an algorithm \emph{Gradient Embedding Perturbation (GEP)} towards training differentially private deep models with decent accuracy. Specifically, in each gradient descent step, GEP first projects individual private gradient into a non-sensitive anchor subspace, producing a low-dimensional gradient embedding and a small-norm residual gradient. Then, GEP perturbs the low-dimensional embedding and the residual gradient separately according to the privacy budget. Such a decomposition permits a small perturbation variance, which greatly helps to break the dimensional barrier of private learning. With GEP, we achieve decent accuracy with low computational cost and modest privacy guarantee for deep models. Especially, with privacy bound $\epsilon=8$, we achieve $74.9\%$ test accuracy on CIFAR10 and $95.1\%$ test accuracy on SVHN, significantly improving over existing results.
Paul Michel, Tatsunori Hashimoto, Graham Neubig
tl;dr: We use generative neural models to define the uncertainty set in distributionally robust optimization, and show that this helps train more robust classifiers
Distributionally robust optimization (DRO) provides a framework for training machine learning models that are able to perform well on a collection of related data distributions (the "uncertainty set"). This is done by solving a min-max game: the model is trained to minimize its maximum expected loss among all distributions in the uncertainty set. While careful design of the uncertainty set is critical to the success of the DRO procedure, previous work has been limited to relatively simple alternatives that keep the min-max optimization problem exactly tractable, such as $f$-divergence balls. In this paper, we argue instead for the use of neural generative models to characterize the worst-case distribution, allowing for more flexible and problem-specific selection of the uncertainty set. However, while simple conceptually, this approach poses a number of implementation and optimization challenges. To circumvent these issues, we propose a relaxation of the KL-constrained inner maximization objective that makes the DRO problem more amenable to gradient-based optimization of large scale generative models, and develop model selection heuristics to guide hyper-parameter search. On both toy settings and realistic NLP tasks, we find that the proposed approach yields models that are more robust than comparable baselines.
Ali Harakeh, Steven L. Waslander
Predictive uncertainty estimation is an essential next step for the reliable deployment of deep object detectors in safety-critical tasks. In this work, we focus on estimating predictive distributions for bounding box regression output with variance networks. We show that in the context of object detection, training variance networks with negative log likelihood (NLL) can lead to high entropy predictive distributions regardless of the correctness of the output mean. We propose to use the energy score as a non-local proper scoring rule and find that when used for training, the energy score leads to better calibrated and lower entropy predictive distributions than NLL. We also address the widespread use of non-proper scoring metrics for evaluating predictive distributions from deep object detectors by proposing an alternate evaluation approach founded on proper scoring rules. Using the proposed evaluation tools, we show that although variance networks can be used to produce high quality predictive distributions, ad-hoc approaches used by seminal object detectors for choosing regression targets during training do not provide wide enough data support for reliable variance learning. We hope that our work helps shift evaluation in probabilistic object detection to better align with predictive uncertainty evaluation in other machine learning domains. Code for all models, evaluation, and datasets is available at:
Simon Carbonnelle, Christophe De Vleeschouwer
tl;dr: This paper provides empirical evidence that deep neural networks are implicitly regularized through their ability to extract meaningful clusters among the samples of a class.
Several works have shown that the regularization mechanisms underlying deep neural networks' generalization performances are still poorly understood. In this paper, we hypothesize that deep neural networks are regularized through their ability to extract meaningful clusters among the samples of a class. This constitutes an implicit form of regularization, as no explicit training mechanisms or supervision target such behaviour. To support our hypothesis, we design four different measures of intraclass clustering, based on the neuron- and layer-level representations of the training data. We then show that these measures constitute accurate predictors of generalization performance across variations of a large set of hyperparameters (learning rate, batch size, optimizer, weight decay, dropout rate, data augmentation, network depth and width).
Daniel Hsu, Ziwei Ji, Matus Telgarsky, Lan Wang
tl;dr: This paper provides a suite of mathematical tools to bound the generalization error of networks which possess low-complexity distillations.
This paper theoretically investigates the following empirical phenomenon: given a high-complexity network with poor generalization bounds, one can distill it into a network with nearly identical predictions but low complexity and vastly smaller generalization bounds. The main contribution is an analysis showing that the original network inherits this good generalization bound from its distillation, assuming the use of well-behaved data augmentation. This bound is presented both in an abstract and in a concrete form, the latter complemented by a reduction technique to handle modern computation graphs featuring convolutional layers, fully-connected layers, and skip connections, to name a few. To round out the story, a (looser) classical uniform convergence analysis of compression is also presented, as well as a variety of experiments on cifar and mnist demonstrating similar generalization performance between the original network and its distillation.
Emilio Parisotto, Russ Salakhutdinov
tl;dr: Actor-Learner Distillation uses an continual form of distillation to attain the high sample-efficiency of transformers while maintaining the reduced total training time of LSTMs in RL applications.
Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on un-accelerated hardware such as CPUs, which likewise restricts model size to prevent intractable experiment run times. These "actor-latency" constrained settings present a major obstruction to the scaling up of model complexity that has recently been extremely successful in supervised learning. To be able to utilize large model capacity while still operating within the limits imposed by the system during acting, we develop an "Actor-Learner Distillation" (ALD) procedure that leverages a continual form of distillation that transfers learning progress from a large capacity learner model to a small capacity actor model. As a case study, we develop this procedure in the context of partially-observable environments, where transformer models have had large improvements over LSTMs recently, at the cost of significantly higher computational complexity. With transformer models as the learner and LSTMs as the actor, we demonstrate in several challenging memory environments that using Actor-Learner Distillation largely recovers the clear sample-efficiency gains of the transformer learner model while maintaining the fast inference and reduced total training time of the LSTM actor model.
Amy Zhang, Shagun Sodhani, Khimya Khetarpal, Joelle Pineau
tl;dr: We propose a new framework for tackling environments with different dynamics in rich observation settings and learning abstractions with this framework for improved generalization performance.
Many control tasks exhibit similar dynamics that can be modeled as having common latent structure. Hidden-Parameter Markov Decision Processes (HiP-MDPs) explicitly model this structure to improve sample efficiency in multi-task settings. However, this setting makes strong assumptions on the observability of the state that limit its application in real-world scenarios with rich observation spaces. In this work, we leverage ideas of common structure from the HiP-MDP setting, and extend it to enable robust state abstractions inspired by Block MDPs. We derive instantiations of this new framework for both multi-task reinforcement learning (MTRL) and meta-reinforcement learning (Meta-RL) settings. Further, we provide transfer and generalization bounds based on task and state similarity, along with sample complexity bounds that depend on the aggregate number of samples across tasks, rather than the number of tasks, a significant improvement over prior work. To further demonstrate efficacy of the proposed method, we empirically compare and show improvement over multi-task and meta-reinforcement learning baselines.
Meng Qu, Junkun Chen, Louis-Pascal Xhonneux, Yoshua Bengio, Jian Tang
tl;dr: Learn Logic Rules for Reasoning on Knowledge Graphs.
This paper studies learning logic rules for reasoning on knowledge graphs. Logic rules provide interpretable explanations when used for prediction as well as being able to generalize to other tasks, and hence are critical to learn. Existing methods either suffer from the problem of searching in a large search space (e.g., neural logic programming) or ineffective optimization due to sparse rewards (e.g., techniques based on reinforcement learning). To address these limitations, this paper proposes a probabilistic model called RNNLogic. RNNLogic treats logic rules as a latent variable, and simultaneously trains a rule generator as well as a reasoning predictor with logic rules. We develop an EM-based algorithm for optimization. In each iteration, the reasoning predictor is updated to explore some generated logic rules for reasoning. Then in the E-step, we select a set of high-quality rules from all generated rules with both the rule generator and reasoning predictor via posterior inference; and in the M-step, the rule generator is updated with the rules selected in the E-step. Experiments on four datasets prove the effectiveness of RNNLogic.
Jeremy Cohen, Simran Kaur, Yuanzhi Li, J Zico Kolter, Ameet Talwalkar
tl;dr: We trained neural networks using full-batch gradient descent -- you won't believe what happens next!
We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability. In this regime, the maximum eigenvalue of the training loss Hessian hovers just above the value $2 / \text{(step size)}$, and the training loss behaves non-monotonically over short timescales, yet consistently decreases over long timescales. Since this behavior is inconsistent with several widespread presumptions in the field of optimization, our findings raise questions as to whether these presumptions are relevant to neural network training. We hope that our findings will inspire future efforts aimed at rigorously understanding optimization at the Edge of Stability.
Satya Narayan Shukla, Benjamin Marlin
tl;dr: This paper presents a new architecture for learning with sparse and irregularly sampled multivariate time series that achieves improved performance than current state-of-the-art methods while providing significantly reduced training times.
Irregular sampling occurs in many time series modeling applications where it presents a significant challenge to standard deep learning models. This work is motivated by the analysis of physiological time series data in electronic health records, which are sparse, irregularly sampled, and multivariate. In this paper, we propose a new deep learning framework for this setting that we call Multi-Time Attention Networks. Multi-Time Attention Networks learn an embedding of continuous time values and use an attention mechanism to produce a fixed-length representation of a time series containing a variable number of observations. We investigate the performance of this framework on interpolation and classification tasks using multiple datasets. Our results show that the proposed approach performs as well or better than a range of baseline and recently proposed models while offering significantly faster training times than current state-of-the-art methods.
Cheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu, Pradeep Kumar Ravikumar, Seungyeon Kim, Sanjiv Kumar, Cho-Jui Hsieh
tl;dr: We propose a suite of objective measurements for evaluating feature based explanations by the notion of robustness analysis; we further derive new explanation that captures different characteristics of explanation comparing to existing methods.
Feature based explanations, that provide importance of each feature towards the model prediction, is arguably one of the most intuitive ways to explain a model. In this paper, we establish a novel set of evaluation criteria for such feature based explanations by robustness analysis. In contrast to existing evaluations which require us to specify some way to "remove" features that could inevitably introduces biases and artifacts, we make use of the subtler notion of smaller adversarial perturbations. By optimizing towards our proposed evaluation criteria, we obtain new explanations that are loosely necessary and sufficient for a prediction. We further extend the explanation to extract the set of features that would move the current prediction to a target class by adopting targeted adversarial attack for the robustness analysis. Through experiments across multiple domains and a user study, we validate the usefulness of our evaluation criteria and our derived explanations.
Shyamgopal Karthik, Ameya Prabhu, Puneet K. Dokania, Vineet Gandhi
tl;dr: Conditional risk framework exploiting the label hierarchy outperforms state of the art and makes a strong baseline for future explorations.
There has been increasing interest in building deep hierarchy-aware classifiers that aim to quantify and reduce the severity of mistakes, and not just reduce the number of errors. The idea is to exploit the label hierarchy (e.g., the WordNet ontology) and consider graph distances as a proxy for mistake severity. Surprisingly, on examining mistake-severity distributions of the top-1 prediction, we find that current state-of-the-art hierarchy-aware deep classifiers do not always show practical improvement over the standard cross-entropy baseline in making better mistakes. The reason for the reduction in average mistake-severity can be attributed to the increase in low-severity mistakes, which may also explain the noticeable drop in their accuracy. To this end, we use the classical Conditional Risk Minimization (CRM) framework for hierarchy-aware classification. Given a cost matrix and a reliable estimate of likelihoods (obtained from a trained network), CRM simply amends mistakes at inference time; it needs no extra hyperparameters and requires adding just a few lines of code to the standard cross-entropy baseline. It significantly outperforms the state-of-the-art and consistently obtains large reductions in the average hierarchical distance of top-$k$ predictions across datasets, with very little loss in accuracy. CRM, because of its simplicity, can be used with any off-the-shelf trained model that provides reliable likelihood estimates.
Lei Chen, Zhengdao Chen, Joan Bruna
tl;dr: We establish a separation in expressive power and flexibility of learning between GNNs and Graph-Augmented MLPs.
From the perspectives of expressive power and learning, this work compares multi-layer Graph Neural Networks (GNNs) with a simplified alternative that we call Graph-Augmented Multi-Layer Perceptrons (GA-MLPs), which first augments node features with certain multi-hop operators on the graph and then applies learnable node-wise functions. From the perspective of graph isomorphism testing, we show both theoretically and numerically that GA-MLPs with suitable operators can distinguish almost all non-isomorphic graphs, just like the Weisfeiler-Lehman (WL) test and GNNs. However, by viewing them as node-level functions and examining the equivalence classes they induce on rooted graphs, we prove a separation in expressive power between GA-MLPs and GNNs that grows exponentially in depth. In particular, unlike GNNs, GA-MLPs are unable to count the number of attributed walks. We also demonstrate via community detection experiments that GA-MLPs can be limited by their choice of operator family, whereas GNNs have higher flexibility in learning.
Zhenyu Liao, Romain Couillet, Michael W. Mahoney
Given a large data matrix, sparsifying, quantizing, and/or performing other entry-wise nonlinear operations can have numerous benefits, ranging from speeding up iterative algorithms for core numerical linear algebra problems to providing nonlinear filters to design state-of-the-art neural network models. Here, we exploit tools from random matrix theory to make precise statements about how the eigenspectrum of a matrix changes under such nonlinear transformations. In particular, we show that very little change occurs in the informative eigenstructure, even under drastic sparsification/quantization, and consequently that very little downstream performance loss occurs when working with very aggressively sparsified or quantized spectral clustering problems. We illustrate how these results depend on the nonlinearity, we characterize a phase transition beyond which spectral clustering becomes possible, and we show when such nonlinear transformations can introduce spurious non-informative eigenvectors.
Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, RISHITA ANUBHAI, Cicero Nogueira dos Santos, Bing Xiang, Stefano Soatto
tl;dr: We propose a unified text-to-text approach to handle a variety of structured prediction tasks in a single model, allowing seamless multi-task training and providing extra benefits on low-resource scenarios.
We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification, semantic role labeling, event extraction, coreference resolution, and dialogue state tracking. Instead of tackling the problem by training task-specific discriminative classifiers, we frame it as a translation task between augmented natural languages, from which the task-relevant information can be easily extracted. Our approach can match or outperform task-specific models on all tasks, and in particular achieves new state-of-the-art results on joint entity and relation extraction (CoNLL04, ADE, NYT, and ACE2005 datasets), relation classification (FewRel and TACRED), and semantic role labeling (CoNLL-2005 and CoNLL-2012). We accomplish this while using the same architecture and hyperparameters for all tasks, and even when training a single model to solve all tasks at the same time (multi-task learning). Finally, we show that our framework can also significantly improve the performance in a low-resource regime, thanks to better use of label semantics.
Erik Jones, Shiori Sagawa, Pang Wei Koh, Ananya Kumar, Percy Liang
Selective classification, in which models can abstain on uncertain predictions, is a natural approach to improving accuracy in settings where errors are costly but abstentions are manageable. In this paper, we find that while selective classification can improve average accuracies, it can simultaneously magnify existing accuracy disparities between various groups within a population, especially in the presence of spurious correlations. We observe this behavior consistently across five vision and NLP datasets. Surprisingly, increasing abstentions can even decrease accuracies on some groups. To better understand this phenomenon, we study the margin distribution, which captures the model’s confidences over all predictions. For symmetric margin distributions, we prove that whether selective classification monotonically improves or worsens accuracy is fully determined by the accuracy at full coverage (i.e., without any abstentions) and whether the distribution satisfies a property we call left-log-concavity. Our analysis also shows that selective classification tends to magnify full-coverage accuracy disparities. Motivated by our analysis, we train distributionally-robust models that achieve similar full-coverage accuracies across groups and show that selective classification uniformly improves each group on these models. Altogether, our results suggest that selective classification should be used with care and underscore the importance of training models to perform equally well across groups at full coverage.
Byung-Jun Lee, Jongmin Lee, Kee-Eung Kim
tl;dr: We present RepB-SDE, a framework for balancing the model representation with stationary distribution estimation, aiming at obtaining a model robust to the distribution shift that arises in off-policy and offline RL.
One of the main challenges in offline and off-policy reinforcement learning is to cope with the distribution shift that arises from the mismatch between the target policy and the data collection policy. In this paper, we focus on a model-based approach, particularly on learning the representation for a robust model of the environment under the distribution shift, which has been first studied by Representation Balancing MDP (RepBM). Although this prior work has shown promising results, there are a number of shortcomings that still hinder its applicability to practical tasks. In particular, we address the curse of horizon exhibited by RepBM, rejecting most of the pre-collected data in long-term tasks. We present a new objective for model learning motivated by recent advances in the estimation of stationary distribution corrections. This effectively overcomes the aforementioned limitation of RepBM, as well as naturally extending to continuous action spaces and stochastic policies. We also present an offline model-based policy optimization using this new objective, yielding the state-of-the-art performance in a representative set of benchmark offline RL tasks.
Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan
tl;dr: We propose a temporal kernel learning approach based on random features and reparameterization to characterize the continuous-time information in deep learning models.
Sequential deep learning models such as RNN, causal CNN and attention mechanism do not readily consume continuous-time information. Discretizing the temporal data, as we show, causes inconsistency even for simple continuous-time processes. Current approaches often handle time in a heuristic manner to be consistent with the existing deep learning architectures and implementations. In this paper, we provide a principled way to characterize continuous-time systems using deep learning tools. Notably, the proposed approach applies to all the major deep learning architectures and requires little modifications to the implementation. The critical insight is to represent the continuous-time system by composing neural networks with a temporal kernel, where we gain our intuition from the recent advancements in understanding deep learning with Gaussian process and neural tangent kernel. To represent the temporal kernel, we introduce the random feature approach and convert the kernel learning problem to spectral density estimation under reparameterization. We further prove the convergence and consistency results even when the temporal kernel is non-stationary, and the spectral density is misspecified. The simulations and real-data experiments demonstrate the empirical effectiveness of our temporal kernel approach in a broad range of settings.
Taylor Whittington Webb, Ishan Sinha, Jonathan Cohen
tl;dr: We introduce a new architecture, the Emergent Symbol Binding Network, that enables rapid learning of abstract rules and strong generalization of those rules to novel entities.
A key aspect of human intelligence is the ability to infer abstract rules directly from high-dimensional sensory data, and to do so given only a limited amount of training experience. Deep neural network algorithms have proven to be a powerful tool for learning directly from high-dimensional data, but currently lack this capacity for data-efficient induction of abstract rules, leading some to argue that symbol-processing mechanisms will be necessary to account for this capacity. In this work, we take a step toward bridging this gap by introducing the Emergent Symbol Binding Network (ESBN), a recurrent network augmented with an external memory that enables a form of variable-binding and indirection. This binding mechanism allows symbol-like representations to emerge through the learning process without the need to explicitly incorporate symbol-processing machinery, enabling the ESBN to learn rules in a manner that is abstracted away from the particular entities to which those rules apply. Across a series of tasks, we show that this architecture displays nearly perfect generalization of learned rules to novel entities given only a limited number of training examples, and outperforms a number of other competitive neural network architectures.
Lin Chen, Sheng Xu
tl;dr: We prove that the reproducing kernel Hilbert spaces of a deep neural tangent kernel and the Laplace kernel include the same set of functions.
We prove that the reproducing kernel Hilbert spaces (RKHS) of a deep neural tangent kernel and the Laplace kernel include the same set of functions, when both kernels are restricted to the sphere $\mathbb{S}^{d-1}$. Additionally, we prove that the exponential power kernel with a smaller power (making the kernel less smooth) leads to a larger RKHS, when it is restricted to the sphere $\mathbb{S}^{d-1}$ and when it is defined on the entire $\mathbb{R}^d$.
Alexia Jolicoeur-Martineau, Rémi Piché-Taillefer, Ioannis Mitliagkas, Remi Tachet des Combes
tl;dr: Combining GANs with score matching and using Consistent Sampling (as an alternative to Langevin dynamics) for improved generative modeling
Denoising Score Matching with Annealed Langevin Sampling (DSM-ALS) has recently found success in generative modeling. The approach works by first training a neural network to estimate the score of a distribution, and then using Langevin dynamics to sample from the data distribution assumed by the score network. Despite the convincing visual quality of samples, this method appears to perform worse than Generative Adversarial Networks (GANs) under the Fréchet Inception Distance, a standard metric for generative models. We show that this apparent gap vanishes when denoising the final Langevin samples using the score network. In addition, we propose two improvements to DSM-ALS: 1) Consistent Annealed Sampling as a more stable alternative to Annealed Langevin Sampling, and 2) a hybrid training formulation, composed of both Denoising Score Matching and adversarial objectives. By combining these two techniques and exploring different network architectures, we elevate score matching methods and obtain results competitive with state-of-the-art image generation on CIFAR-10.
Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma
tl;dr: A simple but effective nerual attention distillation method for backdoor defense.
Deep neural networks (DNNs) are known vulnerable to backdoor attacks, a training time attack that injects a trigger pattern into a small proportion of training data so as to control the model's prediction at the test time. Backdoor attacks are notably dangerous since they do not affect the model's performance on clean examples, yet can fool the model to make the incorrect prediction whenever the trigger pattern appears during testing. In this paper, we propose a novel defense framework Neural Attention Distillation (NAD) to erase backdoor triggers from backdoored DNNs. NAD utilizes a teacher network to guide the finetuning of the backdoored student network on a small clean subset of data such that the intermediate-layer attention of the student network aligns with that of the teacher network. The teacher network can be obtained by an independent finetuning process on the same clean subset. We empirically show, against 6 state-of-the-art backdoor attacks, NAD can effectively erase the backdoor triggers using only 5\% clean training data without causing obvious performance degradation on clean examples. Our code is available at
Changan Chen, Sagnik Majumder, Ziad Al-Halah, Ruohan Gao, Santhosh Kumar Ramakrishnan, Kristen Grauman
tl;dr: We introduce a hierarchical reinforcement learning approach to audio-visual navigation that learns to dynamically set waypoints in an end-to-end fashion
In audio-visual navigation, an agent intelligently travels through a complex, unmapped 3D environment using both sights and sounds to find a sound source (e.g., a phone ringing in another room). Existing models learn to act at a fixed granularity of agent motion and rely on simple recurrent aggregations of the audio observations. We introduce a reinforcement learning approach to audio-visual navigation with two key novel elements: 1) waypoints that are dynamically set and learned end-to-end within the navigation policy, and 2) an acoustic memory that provides a structured, spatially grounded record of what the agent has heard as it moves. Both new ideas capitalize on the synergy of audio and visual data for revealing the geometry of an unmapped space. We demonstrate our approach on two challenging datasets of real-world 3D scenes, Replica and Matterport3D. Our model improves the state of the art by a substantial margin, and our experiments reveal that learning the links between sights, sounds, and space is essential for audio-visual navigation.
Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, Donald Metzler
tl;dr: Better benchmarking for Xformers
Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity. In the recent months, a wide spectrum of efficient, fast Transformers have been proposed to tackle this problem, more often than not claiming superior or comparable model quality to vanilla Transformer models. To this date, there is no well-established consensus on how to evaluate this class of models. Moreover, inconsistent benchmarking on a wide spectrum of tasks and datasets makes it difficult to assess relative model quality amongst many models. This paper proposes a systematic and unified benchmark, Long Range Arena, specifically focused on evaluating model quality under long-context scenarios. Our benchmark is a suite of tasks consisting of sequences ranging from $1K$ to $16K$ tokens, encompassing a wide range of data types and modalities such as text, natural, synthetic images, and mathematical expressions requiring similarity, structural, and visual-spatial reasoning. We systematically evaluate ten well-established long-range Transformer models (Reformers, Linformers, Linear Transformers, Sinkhorn Transformers, Performers, Synthesizers, Sparse Transformers, and Longformers) on our newly proposed benchmark suite. Long Range Arena paves the way towards better understanding this class of efficient Transformer models, facilitates more research in this direction, and presents new challenging tasks to tackle.
Florian Tramer, Dan Boneh
tl;dr: Linear models with handcrafted features outperform end-to-end CNNs for differentially private learning
We demonstrate that differentially private machine learning has not yet reached its ''AlexNet moment'' on many canonical vision tasks: linear models trained on handcrafted features significantly outperform end-to-end deep neural networks for moderate privacy budgets. To exceed the performance of handcrafted features, we show that private learning requires either much more private data, or access to features learned on public data from a similar domain. Our work introduces simple yet strong baselines for differentially private learning that can inform the evaluation of future progress in this area.
Francesco Faccio, Louis Kirsch, Jürgen Schmidhuber
tl;dr: We propose value functions whose inputs include the policy parameters and which can generalize across different policies
Traditional off-policy actor-critic Reinforcement Learning (RL) algorithms learn value functions of a single target policy. However, when value functions are updated to track the learned policy, they forget potentially useful information about old policies. We introduce a class of value functions called Parameter-Based Value Functions (PBVFs) whose inputs include the policy parameters. They can generalize across different policies. PBVFs can evaluate the performance of any policy given a state, a state-action pair, or a distribution over the RL agent's initial states. First we show how PBVFs yield novel off-policy policy gradient theorems. Then we derive off-policy actor-critic algorithms based on PBVFs trained by Monte Carlo or Temporal Difference methods. We show how learned PBVFs can zero-shot learn new policies that outperform any policy seen during training. Finally our algorithms are evaluated on a selection of discrete and continuous control tasks using shallow policies and deep neural networks. Their performance is comparable to state-of-the-art methods.
Xiaoyu Chen, Jiachen Hu, Lihong Li, Liwei Wang
tl;dr: We propose an efficient algorithm with near-optimal regret guarantee for factored MDP, and apply the algorithm to a new formulation of constrained RL.
Reinforcement learning (RL) in episodic, factored Markov decision processes (FMDPs) is studied. We propose an algorithm called FMDP-BF, which leverages the factorization structure of FMDP. The regret of FMDP-BF is shown to be exponentially smaller than that of optimal algorithms designed for non-factored MDPs, and improves on the best previous result for FMDPs~\citep{osband2014near} by a factor of $\sqrt{nH|\mathcal{S}_i|}$, where $|\mathcal{S}_i|$ is the cardinality of the factored state subspace, $H$ is the planning horizon and $n$ is the number of factored transition. To show the optimality of our bounds, we also provide a lower bound for FMDP, which indicates that our algorithm is near-optimal w.r.t. timestep $T$, horizon $H$ and factored state-action subspace cardinality. Finally, as an application, we study a new formulation of constrained RL, known as RL with knapsack constraints (RLwK), and provides the first sample-efficient algorithm based on FMDP-BF.
Thao Nguyen, Maithra Raghu, Simon Kornblith
tl;dr: We show that depth/width variations result in distinctive characteristics in the model internal representations, with resulting consequences for representations and output predictions across different model initializations and architectures.
A key factor in the success of deep neural networks is the ability to scale models to improve performance by varying the architecture depth and width. This simple property of neural network design has resulted in highly effective architectures for a variety of tasks. Nevertheless, there is limited understanding of effects of depth and width on the learned representations. In this paper, we study this fundamental question. We begin by investigating how varying depth and width affects model hidden representations, finding a characteristic block structure in the hidden representations of larger capacity (wider or deeper) models. We demonstrate that this block structure arises when model capacity is large relative to the size of the training set, and is indicative of the underlying layers preserving and propagating the dominant principal component of their representations. This discovery has important ramifications for features learned by different models, namely, representations outside the block structure are often similar across architectures with varying widths and depths, but the block structure is unique to each model. We analyze the output predictions of different model architectures, finding that even when the overall accuracy is similar, wide and deep models exhibit distinctive error patterns and variations across classes.
Zirui Wang, Yulia Tsvetkov, Orhan Firat, Yuan Cao
Massively multilingual models subsuming tens or even hundreds of languages pose great challenges to multi-task optimization. While it is a common practice to apply a language-agnostic procedure optimizing a joint multilingual task objective, how to properly characterize and take advantage of its underlying problem structure for improving optimization efficiency remains under-explored. In this paper, we attempt to peek into the black-box of multilingual optimization through the lens of loss function geometry. We find that gradient similarity measured along the optimization trajectory is an important signal, which correlates well with not only language proximity but also the overall model performance. Such observation helps us to identify a critical limitation of existing gradient-based multi-task learning methods, and thus we derive a simple and scalable optimization procedure, named Gradient Vaccine, which encourages more geometrically aligned parameter updates for close tasks. Empirically, our method obtains significant model performance gains on multilingual machine translation and XTREME benchmark tasks for multilingual language models. Our work reveals the importance of properly measuring and utilizing language proximity in multilingual optimization, and has broader implications for multi-task learning beyond multilingual modeling.
Wenhan Xiong, Xiang Li, Srini Iyer, Jingfei Du, Patrick Lewis, William Yang Wang, Yashar Mehdad, Scott Yih, Sebastian Riedel, Douwe Kiela, Barlas Oguz
tl;dr: We propose a simple yet effective multi-hop dense retrieval approach for answering complex open-domain questions.
We propose a simple and efficient multi-hop dense retrieval approach for answering complex open-domain questions, which achieves state-of-the-art performance on two multi-hop datasets, HotpotQA and multi-evidence FEVER. Contrary to previous work, our method does not require access to any corpus-specific information, such as inter-document hyperlinks or human-annotated entity markers, and can be applied to any unstructured text corpus. Our system also yields a much better efficiency-accuracy trade-off, matching the best published accuracy on HotpotQA while being 10 times faster at inference time.
Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato
tl;dr: We proposed a method to tackle the curse-of-dimensionality issue of kernelized Stein discrepancy with RBF kernel, along with a novel particle inference algorithm resolving the vanishing repulsive issue of Stein variational gradient descent.
Kernelized Stein discrepancy (KSD), though being extensively used in goodness-of-fit tests and model learning, suffers from the curse-of-dimensionality. We address this issue by proposing the sliced Stein discrepancy and its scalable and kernelized variants, which employs kernel-based test functions defined on the optimal one-dimensional projections. When applied to goodness-of-fit tests, extensive experiments show the proposed discrepancy significantly outperforms KSD and various baselines in high dimensions. For model learning, we show its advantages by training an independent component analysis when compared with existing Stein discrepancy baselines. We further propose a novel particle inference method called sliced Stein variational gradient descent (S-SVGD) which alleviates the mode-collapse issue of SVGD in training variational autoencoders.
Zhiyuan Fang, Jianfeng Wang, Lijuan Wang, Lei Zhang, Yezhou Yang, Zicheng Liu
tl;dr: We propose ${\large S}$EED, a self-supervised distillation technique for visual representation learning.
This paper is concerned with self-supervised learning for small models. The problem is motivated by our empirical studies that while the widely used contrastive self-supervised learning method has shown great progress on large model training, it does not work well for small models. To address this problem, we propose a new learning paradigm, named $\textbf{SE}$lf-Sup$\textbf{E}$rvised $\textbf{D}$istillation (${\large S}$EED), where we leverage a larger network (as Teacher) to transfer its representational knowledge into a smaller architecture (as Student) in a self-supervised fashion. Instead of directly learning from unlabeled data, we train a student encoder to mimic the similarity score distribution inferred by a teacher over a set of instances. We show that ${\large S}$EED dramatically boosts the performance of small networks on downstream tasks. Compared with self-supervised baselines, ${\large S}$EED improves the top-1 accuracy from 42.2% to 67.6% on EfficientNet-B0 and from 36.3% to 68.2% on MobileNet-v3-Large on the ImageNet-1k dataset.
Hubert Ramsauer, Bernhard Schäfl, Johannes Lehner, Philipp Seidl, Michael Widrich, Lukas Gruber, Markus Holzleitner, Thomas Adler, David Kreil, Michael K Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter
tl;dr: A novel continuous Hopfield network is proposed whose update rule is the attention mechanism of the transformer model and which can be integrated into deep learning architectures.
We introduce a modern Hopfield network with continuous states and a corresponding update rule. The new Hopfield network can store exponentially (with the dimension of the associative space) many patterns, retrieves the pattern with one update, and has exponentially small retrieval errors. It has three types of energy minima (fixed points of the update): (1) global fixed point averaging over all patterns, (2) metastable states averaging over a subset of patterns, and (3) fixed points which store a single pattern. The new update rule is equivalent to the attention mechanism used in transformers. This equivalence enables a characterization of the heads of transformer models. These heads perform in the first layers preferably global averaging and in higher layers partial averaging via metastable states. The new modern Hopfield network can be integrated into deep learning architectures as layers to allow the storage of and access to raw input data, intermediate results, or learned prototypes. These Hopfield layers enable new ways of deep learning, beyond fully-connected, convolutional, or recurrent networks, and provide pooling, memory, association, and attention mechanisms. We demonstrate the broad applicability of the Hopfield layers across various domains. Hopfield layers improved state-of-the-art on three out of four considered multiple instance learning problems as well as on immune repertoire classification with several hundreds of thousands of instances. On the UCI benchmark collections of small classification tasks, where deep learning methods typically struggle, Hopfield layers yielded a new state-of-the-art when compared to different machine learning methods. Finally, Hopfield layers achieved state-of-the-art on two drug design datasets. The implementation is available at: \url{}
Valeriia Cherepanova, Micah Goldblum, Harrison Foley, Shiyuan Duan, John P Dickerson, Gavin Taylor, Tom Goldstein
tl;dr: We leverage adversarial attacks in our tool, LowKey, which protects social media users from invasive mass surveillance systems.
Facial recognition systems are increasingly deployed by private corporations, government agencies, and contractors for consumer services and mass surveillance programs alike. These systems are typically built by scraping social media profiles for user images. Adversarial perturbations have been proposed for bypassing facial recognition systems. However, existing methods fail on full-scale systems and commercial APIs. We develop our own adversarial filter that accounts for the entire image processing pipeline and is demonstrably effective against industrial-grade pipelines that include face detection and large scale databases. Additionally, we release an easy-to-use webtool that significantly degrades the accuracy of Amazon Rekognition and the Microsoft Azure Face Recognition API, reducing the accuracy of each to below 1%.
Chulhee Yun, Shankar Krishnan, Hossein Mobahi
tl;dr: We propose a unifying framework for analyzing implicit bias of linear networks and show theorems that extend existing results with less convergence assumptions.
We study the implicit bias of gradient flow (i.e., gradient descent with infinitesimal step size) on linear neural network training. We propose a tensor formulation of neural networks that includes fully-connected, diagonal, and convolutional networks as special cases, and investigate the linear version of the formulation called linear tensor networks. With this formulation, we can characterize the convergence direction of the network parameters as singular vectors of a tensor defined by the network. For $L$-layer linear tensor networks that are orthogonally decomposable, we show that gradient flow on separable classification finds a stationary point of the $\ell_{2/L}$ max-margin problem in a "transformed" input space defined by the network. For underdetermined regression, we prove that gradient flow finds a global minimum which minimizes a norm-like function that interpolates between weighted $\ell_1$ and $\ell_2$ norms in the transformed input space. Our theorems subsume existing results in the literature while removing standard convergence assumptions. We also provide experiments that corroborate our analysis.
Tolga Ergen, Mert Pilanci
tl;dr: We study the training problem for various CNN architectures with ReLU activations and introduce equivalent finite dimensional convex formulations that can be used to globally optimize these architectures.
We study training of Convolutional Neural Networks (CNNs) with ReLU activations and introduce exact convex optimization formulations with a polynomial complexity with respect to the number of data samples, the number of neurons, and data dimension. More specifically, we develop a convex analytic framework utilizing semi-infinite duality to obtain equivalent convex optimization problems for several two- and three-layer CNN architectures. We first prove that two-layer CNNs can be globally optimized via an $\ell_2$ norm regularized convex program. We then show that multi-layer circular CNN training problems with a single ReLU layer are equivalent to an $\ell_1$ regularized convex program that encourages sparsity in the spectral domain. We also extend these results to three-layer CNNs with two ReLU layers. Furthermore, we present extensions of our approach to different pooling methods, which elucidates the implicit architectural bias as convex regularizers.
Veronika Thost, Jie Chen
tl;dr: We propose DAGNN, a graph neural network tailored to directed acyclic graphs that outperforms conventional GNNs by leveraging the partial order as strong inductive bias besides other suitable architectural features.
Graph-structured data ubiquitously appears in science and engineering. Graph neural networks (GNNs) are designed to exploit the relational inductive bias exhibited in graphs; they have been shown to outperform other forms of neural networks in scenarios where structure information supplements node features. The most common GNN architecture aggregates information from neighborhoods based on message passing. Its generality has made it broadly applicable. In this paper, we focus on a special, yet widely used, type of graphs---DAGs---and inject a stronger inductive bias---partial ordering---into the neural network design. We propose the directed acyclic graph neural network, DAGNN, an architecture that processes information according to the flow defined by the partial order. DAGNN can be considered a framework that entails earlier works as special cases (e.g., models for trees and models updating node representations recurrently), but we identify several crucial components that prior architectures lack. We perform comprehensive experiments, including ablation studies, on representative DAG datasets (i.e., source code, neural architectures, and probabilistic graphical models) and demonstrate the superiority of DAGNN over simpler DAG architectures as well as general graph architectures.
Carles Domingo-Enrich, Fabian Pedregosa, Damien Scieur
tl;dr: We extend the framework of average-case optimal first-order methods to problems with non-symmetric matrices, which naturally arise in equilibrium finding for games.
Advances in generative modeling and adversarial learning have given rise to renewed interest in smooth games. However, the absence of symmetry in the matrix of second derivatives poses challenges that are not present in the classical minimization framework. While a rich theory of average-case analysis has been developed for minimization problems, little is known in the context of smooth games. In this work we take a first step towards closing this gap by developing average-case optimal first-order methods for a subset of smooth games. We make the following three main contributions. First, we show that for zero-sum bilinear games the average-case optimal method is the optimal method for the minimization of the Hamiltonian. Second, we provide an explicit expression for the optimal method corresponding to normal matrices, potentially non-symmetric. Finally, we specialize it to matrices with eigenvalues located in a disk and show a provable speed-up compared to worst-case optimal algorithms. We illustrate our findings through benchmarks with a varying degree of mismatch with our assumptions.
Kaiyang Zhou, Yongxin Yang, Yu Qiao, Tao Xiang
tl;dr: MixStyle makes CNNs more domain-generalizable by mixing instance-level feature statistics of training samples across domains.
Though convolutional neural networks (CNNs) have demonstrated remarkable ability in learning discriminative features, they often generalize poorly to unseen domains. Domain generalization aims to address this problem by learning from a set of source domains a model that is generalizable to any unseen domain. In this paper, a novel approach is proposed based on probabilistically mixing instance-level feature statistics of training samples across source domains. Our method, termed MixStyle, is motivated by the observation that visual domain is closely related to image style (e.g., photo vs.~sketch images). Such style information is captured by the bottom layers of a CNN where our proposed style-mixing takes place. Mixing styles of training instances results in novel domains being synthesized implicitly, which increase the domain diversity of the source domains, and hence the generalizability of the trained model. MixStyle fits into mini-batch training perfectly and is extremely easy to implement. The effectiveness of MixStyle is demonstrated on a wide range of tasks including category classification, instance retrieval and reinforcement learning.
Seungjun Lee, Haesang Yang, Woojae Seong
tl;dr: We introduce meta-learning algorithms to identify the shared representation of Hamiltonian systems.
Hamiltonian mechanics is an effective tool to represent many physical processes with concise yet well-generalized mathematical expressions. A well-modeled Hamiltonian makes it easy for researchers to analyze and forecast many related phenomena that are governed by the same physical law. However, in general, identifying a functional or shared expression of the Hamiltonian is very difficult. It requires carefully designed experiments and the researcher's insight that comes from years of experience. We propose that meta-learning algorithms can be potentially powerful data-driven tools for identifying the physical law governing Hamiltonian systems without any mathematical assumptions on the representation, but with observations from a set of systems governed by the same physical law. We show that a well meta-trained learner can identify the shared representation of the Hamiltonian by evaluating our method on several types of physical systems with various experimental settings.
XINJIE FAN, Shujian Zhang, Korawat Tanwisuth, Xiaoning Qian, Mingyuan Zhou
tl;dr: We propose contextual dropout as a scalable sample-dependent dropout method, which makes the dropout probabilities depend on the input covariates of each data sample.
Dropout has been demonstrated as a simple and effective module to not only regularize the training process of deep neural networks, but also provide the uncertainty estimation for prediction. However, the quality of uncertainty estimation is highly dependent on the dropout probabilities. Most current models use the same dropout distributions across all data samples due to its simplicity. Despite the potential gains in the flexibility of modeling uncertainty, sample-dependent dropout, on the other hand, is less explored as it often encounters scalability issues or involves non-trivial model changes. In this paper, we propose contextual dropout with an efficient structural design as a simple and scalable sample-dependent dropout module, which can be applied to a wide range of models at the expense of only slightly increased memory and computational cost. We learn the dropout probabilities with a variational objective, compatible with both Bernoulli dropout and Gaussian dropout. We apply the contextual dropout module to various models with applications to image classification and visual question answering and demonstrate the scalability of the method with large-scale datasets, such as ImageNet and VQA 2.0. Our experimental results show that the proposed method outperforms baseline methods in terms of both accuracy and quality of uncertainty estimation.
Junyi Zhu, Matthew B. Blaschko
Federated learning frameworks have been regarded as a promising approach to break the dilemma between demands on privacy and the promise of learning from large collections of distributed data. Many such frameworks only ask collaborators to share their local update of a common model, i.e. gradients with respect to locally stored data, instead of exposing their raw data to other collaborators. However, recent optimization-based gradient attacks show that raw data can often be accurately recovered from gradients. It has been shown that minimizing the Euclidean distance between true gradients and those calculated from estimated data is often effective in fully recovering private data. However, there is a fundamental lack of theoretical understanding of how and when gradients can lead to unique recovery of original data. Our research fills this gap by providing a closed-form recursive procedure to recover data from gradients in deep neural networks. We name it Recursive Gradient Attack on Privacy (R-GAP). Experimental results demonstrate that R-GAP works as well as or even better than optimization-based approaches at a fraction of the computation under certain conditions. Additionally, we propose a Rank Analysis method, which can be used to estimate the risk of gradient attacks inherent in certain network architectures, regardless of whether an optimization-based or closed-form-recursive attack is used. Experimental results demonstrate the utility of the rank analysis towards improving the network's security. Source code is available for download from
Gregor N. C. Simm, Robert Pinsler, Gábor Csányi, José Miguel Hernández-Lobato
tl;dr: Covariant actor-critic based on spherical harmonics that exploits symmetries to design molecules in 3D
Automating molecular design using deep reinforcement learning (RL) has the potential to greatly accelerate the search for novel materials. Despite recent progress on leveraging graph representations to design molecules, such methods are fundamentally limited by the lack of three-dimensional (3D) information. In light of this, we propose a novel actor-critic architecture for 3D molecular design that can generate molecular structures unattainable with previous approaches. This is achieved by exploiting the symmetries of the design process through a rotationally covariant state-action representation based on a spherical harmonics series expansion. We demonstrate the benefits of our approach on several 3D molecular design tasks, where we find that building in such symmetries significantly improves generalization and the quality of generated molecules.
Andrey Malinin, Mark Gales
tl;dr: A Deep Investigation of Ensemble-based Uncertainty Estimation for Autoregressive ASR and NMT models.
Uncertainty estimation is important for ensuring safety and robustness of AI systems. While most research in the area has focused on un-structured prediction tasks, limited work has investigated general uncertainty estimation approaches for structured prediction. Thus, this work aims to investigate uncertainty estimation for structured prediction tasks within a single unified and interpretable probabilistic ensemble-based framework. We consider: uncertainty estimation for sequence data at the token-level and complete sequence-level; interpretations for, and applications of, various measures of uncertainty; and discuss both the theoretical and practical challenges associated with obtaining them. This work also provides baselines for token-level and sequence-level error detection, and sequence-level out-of-domain input detection on the WMT’14 English-French and WMT’17 English-German translation and LibriSpeech speech recognition datasets.
Kapil Vaidya, Eric Knorr, Michael Mitzenmacher, Tim Kraska
Bloom filters are space-efficient probabilistic data structures that are used to test whether an element is a member of a set, and may return false positives. Recently, variations referred to as learned Bloom filters were developed that can provide improved performance in terms of the rate of false positives, by using a learned model for the represented set. However, previous methods for learned Bloom filters do not take full advantage of the learned model. Here we show how to frame the problem of optimal model utilization as an optimization problem, and using our framework derive algorithms that can achieve near-optimal performance in many cases.
Yannis Flet-Berliac, reda ouhamma, odalric-ambrym maillard, Philippe Preux
tl;dr: We introduce a method to improve the learning of the critic in the actor-critic framework.
Policy gradient algorithms have proven to be successful in diverse decision making and control tasks. However, these methods suffer from high sample complexity and instability issues. In this paper, we address these challenges by providing a different approach for training the critic in the actor-critic framework. Our work builds on recent studies indicating that traditional actor-critic algorithms do not succeed in fitting the true value function, calling for the need to identify a better objective for the critic. In our method, the critic uses a new state-value (resp. state-action-value) function approximation that learns the value of the states (resp. state-action pairs) relative to their mean value rather than the absolute value as in conventional actor-critic. We prove the theoretical consistency of the new gradient estimator and observe dramatic empirical improvement across a variety of continuous control tasks and algorithms. Furthermore, we validate our method in tasks with sparse rewards, where we provide experimental evidence and theoretical insights.
Justin Fu, Sergey Levine
tl;dr: Offline, data-driven optimization using normalized maximum likelihood to produce robust function estimates.
In this work we consider data-driven optimization problems where one must maximize a function given only queries at a fixed set of points. This problem setting emerges in many domains where function evaluation is a complex and expensive process, such as in the design of materials, vehicles, or neural network architectures. Because the available data typically only covers a small manifold of the possible space of inputs, a principal challenge is to be able to construct algorithms that can reason about uncertainty and out-of-distribution values, since a naive optimizer can easily exploit an estimated model to return adversarial inputs. We propose to tackle the MBO problem by leveraging the normalized maximum-likelihood (NML) estimator, which provides a principled approach to handling uncertainty and out-of-distribution inputs. While in the standard formulation NML is intractable, we propose a tractable approximation that allows us to scale our method to high-capacity neural network models. We demonstrate that our method can effectively optimize high-dimensional design problems in a variety of disciplines such as chemistry, biology, and materials engineering.
Ayya Alieva, Aiden Aceves, Jialin Song, Stephen Mayo, Yisong Yue, Yuxin Chen
tl;dr: A data-driven sequential decision making framework based on a novel submodular-regularized loss.
Many sequential decision making tasks can be viewed as combinatorial optimization problems over a large number of actions. When the cost of evaluating an action is high, even a greedy algorithm, which iteratively picks the best action given the history, is prohibitive to run. In this paper, we aim to learn a greedy heuristic for sequentially selecting actions as a surrogate for invoking the expensive oracle when evaluating an action. In particular, we focus on a class of combinatorial problems that can be solved via submodular maximization (either directly on the objective function or via submodular surrogates). We introduce a data-driven optimization framework based on the submodular-norm loss, a novel loss function that encourages the resulting objective to exhibit diminishing returns. Our framework outputs a surrogate objective that is efficient to train, approximately submodular, and can be made permutation-invariant. The latter two properties allow us to prove strong approximation guarantees for the learned greedy heuristic. Furthermore, we show that our model can be easily integrated with modern deep imitation learning pipelines for sequential prediction tasks. We demonstrate the performance of our algorithm on a variety of batched and sequential optimization tasks, including set cover, active learning, and Bayesian optimization for protein engineering.
Mingyang Yi, Lu Hou, Lifeng Shang, Xin Jiang, Qun Liu, Zhi-Ming Ma
tl;dr: a new reweighting strategy on augmented samples
Data augmentation is an effective technique to improve the generalization of deep neural networks. However, previous data augmentation methods usually treat the augmented samples equally without considering their individual impacts on the model. To address this, for the augmented samples from the same training example, we propose to assign different weights to them. We construct the maximal expected loss which is the supremum over any reweighted loss on augmented samples. Inspired by adversarial training, we minimize this maximal expected loss (MMEL) and obtain a simple and interpretable closed-form solution: more attention should be paid to augmented samples with large loss values (i.e., harder examples). Minimizing this maximal expected loss enables the model to perform well under any reweighting strategy. The proposed method can generally be applied on top of any data augmentation methods. Experiments are conducted on both natural language understanding tasks with token-level data augmentation, and image classification tasks with commonly-used image augmentation techniques like random crop and horizontal flip. Empirical results show that the proposed method improves the generalization performance of the model.
Haibo Yang, Minghong Fang, Jia Liu
Federated learning (FL) is a distributed machine learning architecture that leverages a large number of workers to jointly learn a model with decentralized data. FL has received increasing attention in recent years thanks to its data privacy protection, communication efficiency and a linear speedup for convergence in training (i.e., convergence performance increases linearly with respect to the number of workers). However, existing studies on linear speedup for convergence are only limited to the assumptions of i.i.d. datasets across workers and/or full worker participation, both of which rarely hold in practice. So far, it remains an open question whether or not the linear speedup for convergence is achievable under non-i.i.d. datasets with partial worker participation in FL. In this paper, we show that the answer is affirmative. Specifically, we show that the federated averaging (FedAvg) algorithm (with two-sided learning rates) on non-i.i.d. datasets in non-convex settings achieves a convergence rate $\mathcal{O}(\frac{1}{\sqrt{mKT}} + \frac{1}{T})$ for full worker participation and a convergence rate $\mathcal{O}(\frac{\sqrt{K}}{\sqrt{nT}} + \frac{1}{T})$ for partial worker participation, where $K$ is the number of local steps, $T$ is the number of total communication rounds, $m$ is the total worker number and $n$ is the worker number in one communication round if for partial worker participation. Our results also reveal that the local steps in FL could help the convergence and show that the maximum number of local steps can be improved to $T/m$ in full worker participation. We conduct extensive experiments on MNIST and CIFAR-10 to verify our theoretical results.
Xinran Wang, Yu Xiang, Jun Gao, Jie Ding
tl;dr: We propose information laundering, a novel framework for enhancing model privacy.
In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be deployed for public use. The private model can be obtained from general learning methods, and its deployment means that it will return a deterministic or random response for a given input query. An information-laundered model consists of probabilistic components that deliberately maneuver the intended input and output for queries of the model, so the model's adversarial acquisition is less likely. Under the proposed framework, we develop an information-theoretic principle to quantify the fundamental tradeoffs between model utility and privacy leakage and derive the optimal design.
Pau de Jorge, Amartya Sanyal, Harkirat Behl, Philip Torr, Grégory Rogez, Puneet K. Dokania
tl;dr: We find performance of current methods for pruning at initialization plummets at high sparsity levels, we study the possible reasons and present a more robust method overall.
Recent studies have shown that skeletonization (pruning parameters) of networks at initialization provides all the practical benefits of sparsity both at inference and training time, while only marginally degrading their performance. However, we observe that beyond a certain level of sparsity (approx 95%), these approaches fail to preserve the network performance, and to our surprise, in many cases perform even worse than trivial random pruning. To this end, we propose an objective to find a skeletonized network with maximum foresight connection sensitivity (FORCE) whereby the trainability, in terms of connection sensitivity, of a pruned network is taken into consideration. We then propose two approximate procedures to maximize our objective (1) Iterative SNIP: allows parameters that were unimportant at earlier stages of skeletonization to become important at later stages; and (2) FORCE: iterative process that allows exploration by allowing already pruned parameters to resurrect at later stages of skeletonization. Empirical analysis on a large suite of experiments show that our approach, while providing at least as good performance as other recent approaches on moderate pruning levels, provide remarkably improved performance on high pruning levels (could remove up to 99.5% parameters while keeping the networks trainable).
Lizhen Nie, Mao Ye, qiang liu, Dan Nicolae
tl;dr: We propose a varying coefficient network and a functional targeted regularization for estimating continuous treatment.
Motivated by the rising abundance of observational data with continuous treatments, we investigate the problem of estimating the average dose-response curve (ADRF). Available parametric methods are limited in their model space, and previous attempts in leveraging neural network to enhance model expressiveness relied on partitioning continuous treatment into blocks and using separate heads for each block; this however produces in practice discontinuous ADRFs. Therefore, the question of how to adapt the structure and training of neural network to estimate ADRFs remains open. This paper makes two important contributions. First, we propose a novel varying coefficient neural network (VCNet) that improves model expressiveness while preserving continuity of the estimated ADRF. Second, to improve finite sample performance, we generalize targeted regularization to obtain a doubly robust estimator of the whole ADRF curve.
Changhao Shi, Chester Holtz, Gal Mishne
Deep neural networks are known to be vulnerable to adversarial examples, where a perturbation in the input space leads to an amplified shift in the latent network representation. In this paper, we combine canonical supervised learning with self-supervised representation learning, and present Self-supervised Online Adversarial Purification (SOAP), a novel defense strategy that uses a self-supervised loss to purify adversarial examples at test-time. Our approach leverages the label-independent nature of self-supervised signals and counters the adversarial perturbation with respect to the self-supervised tasks. SOAP yields competitive robust accuracy against state-of-the-art adversarial training and purification methods, with considerably less training complexity. In addition, our approach is robust even when adversaries are given the knowledge of the purification defense strategy. To the best of our knowledge, our paper is the first that generalizes the idea of using self-supervised signals to perform online test-time purification.
Benjamin Ehret, Christian Henning, Maria Cervera, Alexander Meulemans, Johannes Von Oswald, Benjamin F Grewe
tl;dr: This paper studies the behavior of established approaches to the problem of continual learning in the context of recurrent neural networks.
While a diverse collection of continual learning (CL) methods has been proposed to prevent catastrophic forgetting, a thorough investigation of their effectiveness for processing sequential data with recurrent neural networks (RNNs) is lacking. Here, we provide the first comprehensive evaluation of established CL methods on a variety of sequential data benchmarks. Specifically, we shed light on the particularities that arise when applying weight-importance methods, such as elastic weight consolidation, to RNNs. In contrast to feedforward networks, RNNs iteratively reuse a shared set of weights and require working memory to process input samples. We show that the performance of weight-importance methods is not directly affected by the length of the processed sequences, but rather by high working memory requirements, which lead to an increased need for stability at the cost of decreased plasticity for learning subsequent tasks. We additionally provide theoretical arguments supporting this interpretation by studying linear RNNs. Our study shows that established CL methods can be successfully ported to the recurrent case, and that a recent regularization approach based on hypernetworks outperforms weight-importance methods, thus emerging as a promising candidate for CL in RNNs. Overall, we provide insights on the differences between CL in feedforward networks and RNNs, while guiding towards effective solutions to tackle CL on sequential data.
Naoyuki Terashita, Hiroki Ohashi, Yuichi Nonaka, Takashi Kanemaru
tl;dr: We propose an influence estimation method which predicts how GAN's output changes if an training instance is abesent, and propose to evaluate harmfulness of the instance by estimating how its absence improves GAN evaluation metric.
Identifying harmful instances, whose absence in a training dataset improves model performance, is important for building better machine learning models. Although previous studies have succeeded in estimating harmful instances under supervised settings, they cannot be trivially extended to generative adversarial networks (GANs). This is because previous approaches require that (i) the absence of a training instance directly affects the loss value and that (ii) the change in the loss directly measures the harmfulness of the instance for the performance of a model. In GAN training, however, neither of the requirements is satisfied. This is because, (i) the generator’s loss is not directly affected by the training instances as they are not part of the generator's training steps, and (ii) the values of GAN's losses normally do not capture the generative performance of a model. To this end, (i) we propose an influence estimation method that uses the Jacobian of the gradient of the generator's loss with respect to the discriminator’s parameters (and vice versa) to trace how the absence of an instance in the discriminator’s training affects the generator’s parameters, and (ii) we propose a novel evaluation scheme, in which we assess harmfulness of each training instance on the basis of how GAN evaluation metric (e.g., inception score) is expected to change due to the removal of the instance. We experimentally verified that our influence estimation method correctly inferred the changes in GAN evaluation metrics. We also demonstrated that the removal of the identified harmful instances effectively improved the model’s generative performance with respect to various GAN evaluation metrics.
Michael R Zhang, Thomas Paine, Ofir Nachum, Cosmin Paduraru, George Tucker, ziyu wang, Mohammad Norouzi
tl;dr: We demonstrate autoregressive dynamics models outperform standard feedforward models and other baselines in offline policy evaluation and optimization.
Standard dynamics models for continuous control make use of feedforward computation to predict the conditional distribution of next state and reward given current state and action using a multivariate Gaussian with a diagonal covariance structure. This modeling choice assumes that different dimensions of the next state and reward are conditionally independent given the current state and action and may be driven by the fact that fully observable physics-based simulation environments entail deterministic transition dynamics. In this paper, we challenge this conditional independence assumption and propose a family of expressive autoregressive dynamics models that generate different dimensions of the next state and reward sequentially conditioned on previous dimensions. We demonstrate that autoregressive dynamics models indeed outperform standard feedforward models in log-likelihood on heldout transitions. Furthermore, we compare different model-based and model-free off-policy evaluation (OPE) methods on RL Unplugged, a suite of offline MuJoCo datasets, and find that autoregressive dynamics models consistently outperform all baselines, achieving a new state-of-the-art. Finally, we show that autoregressive dynamics models are useful for offline policy optimization by serving as a way to enrich the replay buffer through data augmentation and improving performance using model-based planning.
Edgar Schönfeld, Vadim Sushko, Dan Zhang, Juergen Gall, Bernt Schiele, Anna Khoreva
tl;dr: We propose OASIS, a novel model for multi-modal semantic image synthesis, improving over previous methods in terms of image quality and diversity while only using adversarial supervision.
Despite their recent successes, GAN models for semantic image synthesis still suffer from poor image quality when trained with only adversarial supervision. Historically, additionally employing the VGG-based perceptual loss has helped to overcome this issue, significantly improving the synthesis quality, but at the same time limiting the progress of GAN models for semantic image synthesis. In this work, we propose a novel, simplified GAN model, which needs only adversarial supervision to achieve high quality results. We re-design the discriminator as a semantic segmentation network, directly using the given semantic label maps as the ground truth for training. By providing stronger supervision to the discriminator as well as to the generator through spatially- and semantically-aware discriminator feedback, we are able to synthesize images of higher fidelity with better alignment to their input label maps, making the use of the perceptual loss superfluous. Moreover, we enable high-quality multi-modal image synthesis through global and local sampling of a 3D noise tensor injected into the generator, which allows complete or partial image change. We show that images synthesized by our model are more diverse and follow the color and texture distributions of real images more closely. We achieve an average improvement of $6$ FID and $5$ mIoU points over the state of the art across different datasets using only adversarial supervision.
Garrett Honke, Irina Higgins, Nina Thigpen, Vladimir Miskovic, Katie Link, Sunny Duan, Pramod Gupta, Julia Klawohn, Greg Hajcak
tl;dr: We use disentangled representations of EEG signals to improve performance on clinical classification tasks, provide interpretable recommendations for post-hoc analysis and allow for extraction of ERPs from novel single EEG trajectories.
Despite extensive standardization, diagnostic interviews for mental health disorders encompass substantial subjective judgment. Previous studies have demonstrated that EEG-based neural measures can function as reliable objective correlates of depression, or even predictors of depression and its course. However, their clinical utility has not been fully realized because of 1) the lack of automated ways to deal with the inherent noise associated with EEG data at scale, and 2) the lack of knowledge of which aspects of the EEG signal may be markers of a clinical disorder. Here we adapt an unsupervised pipeline from the recent deep representation learning literature to address these problems by 1) learning a disentangled representation using $\beta$-VAE to denoise the signal, and 2) extracting interpretable features associated with a sparse set of clinical labels using a Symbol-Concept Association Network (SCAN). We demonstrate that our method is able to outperform the canonical hand-engineered baseline classification method on a number of factors, including participant age and depression diagnosis. Furthermore, our method recovers a representation that can be used to automatically extract denoised Event Related Potentials (ERPs) from novel, single EEG trajectories, and supports fast supervised re-mapping to various clinical labels, allowing clinicians to re-use a single EEG representation regardless of updates to the standardized diagnostic system. Finally, single factors of the learned disentangled representations often correspond to meaningful markers of clinical factors, as automatically detected by SCAN, allowing for human interpretability and post-hoc expert analysis of the recommendations made by the model.
Erik Scharwächter, Jonathan Lennartz, Emmanuel Müller
tl;dr: We propose an architecture for effective gradient-based learning of segmented models for sequential data.
Segmented models are widely used to describe non-stationary sequential data with discrete change points. Their estimation usually requires solving a mixed discrete-continuous optimization problem, where the segmentation is the discrete part and all other model parameters are continuous. A number of estimation algorithms have been developed that are highly specialized for their specific model assumptions. The dependence on non-standard algorithms makes it hard to integrate segmented models in state-of-the-art deep learning architectures that critically depend on gradient-based optimization techniques. In this work, we formulate a relaxed variant of segmented models that enables joint estimation of all model parameters, including the segmentation, with gradient descent. We build on recent advances in learning continuous warping functions and propose a novel family of warping functions based on the two-sided power (TSP) distribution. TSP-based warping functions are differentiable, have simple closed-form expressions, and can represent segmentation functions exactly. Our formulation includes the important class of segmented generalized linear models as a special case, which makes it highly versatile. We use our approach to model the spread of COVID-19 with Poisson regression, apply it on a change point detection task, and learn classification models with concept drift. The experiments show that our approach effectively learns all these tasks with standard algorithms for gradient descent.
Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, Zhaopeng Tu
tl;dr: We reveal the side effect of knowledge distillation from lexical choice perspective for Non-autoregressvie machine translation, and then propose a simple yet effective approach to improve it.
Knowledge distillation (KD) is essential for training non-autoregressive translation (NAT) models by reducing the complexity of the raw data with an autoregressive teacher model. In this study, we empirically show that as a side effect of this training, the lexical choice errors on low-frequency words are propagated to the NAT model from the teacher model. To alleviate this problem, we propose to expose the raw data to NAT models to restore the useful information of low-frequency words, which are missed in the distilled data. To this end, we introduce an extra Kullback-Leibler divergence term derived by comparing the lexical choice of NAT model and that embedded in the raw data. Experimental results across language pairs and model architectures demonstrate the effectiveness and universality of the proposed approach. Extensive analyses confirm our claim that our approach improves performance by reducing the lexical choice errors on low-frequency words. Encouragingly, our approach pushes the SOTA NAT performance on the WMT14 English-German and WMT16 Romanian-English datasets up to 27.8 and 33.8 BLEU points, respectively.
Ruiqi Gao, Yang Song, Ben Poole, Ying Nian Wu, Diederik P Kingma
tl;dr: We present a diffusion recovery likelihood method to tractably learn and sample from a sequence of EBMs based on a diffusion process. High sample quality, stable long-run MCMC chains and good estimation of likelihood.
While energy-based models (EBMs) exhibit a number of desirable properties, training and sampling on high-dimensional datasets remains challenging. Inspired by recent progress on diffusion probabilistic models, we present a diffusion recovery likelihood method to tractably learn and sample from a sequence of EBMs trained on increasingly noisy versions of a dataset. Each EBM is trained with recovery likelihood, which maximizes the conditional probability of the data at a certain noise level given their noisy versions at a higher noise level. Optimizing recovery likelihood is more tractable than marginal likelihood, as sampling from the conditional distributions is much easier than sampling from the marginal distributions. After training, synthesized images can be generated by the sampling process that initializes from Gaussian white noise distribution and progressively samples the conditional distributions at decreasingly lower noise levels. Our method generates high fidelity samples on various image datasets. On unconditional CIFAR-10 our method achieves FID 9.58 and inception score 8.30, superior to the majority of GANs. Moreover, we demonstrate that unlike previous work on EBMs, our long-run MCMC samples from the conditional distributions do not diverge and still represent realistic images, allowing us to accurately estimate the normalized density of data even for high-dimensional datasets. Our implementation is available at \url{}.
Yaling Tao, Kentaro Takagi, Kouta Nakata
tl;dr: We present a clustering-friendly representation learning method using instance discrimination and feature decorrelation, which achieves accuracy of 81.5% and 95.4% on CIFAR-10 and ImageNet-10, respectively, far above state-of-the-art values.
Clustering is one of the most fundamental tasks in machine learning. Recently, deep clustering has become a major trend in clustering techniques. Representation learning often plays an important role in the effectiveness of deep clustering, and thus can be a principal cause of performance degradation. In this paper, we propose a clustering-friendly representation learning method using instance discrimination and feature decorrelation. Our deep-learning-based representation learning method is motivated by the properties of classical spectral clustering. Instance discrimination learns similarities among data and feature decorrelation removes redundant correlation among features. We utilize an instance discrimination method in which learning individual instance classes leads to learning similarity among instances. Through detailed experiments and examination, we show that the approach can be adapted to learning a latent space for clustering. We design novel softmax-formulated decorrelation constraints for learning. In evaluations of image clustering using CIFAR-10 and ImageNet-10, our method achieves accuracy of 81.5% and 95.4%, respectively. We also show that the softmax-formulated constraints are compatible with various neural networks.
Adam Fisch, Tal Schuster, Tommi S. Jaakkola, Regina Barzilay
tl;dr: This work proposes two complementary techniques for improving the efficiency of conformal prediction in large-scale domains---while still retaining performance guarantees.
In this paper, we present a novel approach for conformal prediction (CP), in which we aim to identify a set of promising prediction candidates---in place of a single prediction. This set is guaranteed to contain a correct answer with high probability, and is well-suited for many open-ended classification tasks. In the standard CP paradigm, the predicted set can often be unusably large and also costly to obtain. This is particularly pervasive in settings where the correct answer is not unique, and the number of total possible answers is high. We first expand the CP correctness criterion to allow for additional, inferred "admissible" answers, which can substantially reduce the size of the predicted set while still providing valid performance guarantees. Second, we amortize costs by conformalizing prediction cascades, in which we aggressively prune implausible labels early on by using progressively stronger classifiers---again, while still providing valid performance guarantees. We demonstrate the empirical effectiveness of our approach for multiple applications in natural language processing and computational chemistry for drug discovery.
Hao Cheng, Zhaowei Zhu, Xingyu Li, Yifei Gong, Xing Sun, Yang Liu
tl;dr: This paper proposes a dynamic sample sieve method with strong theoretical guarantees to avoid overfitting to instance-based label noise.
Human-annotated labels are often prone to noise, and the presence of such noise will degrade the performance of the resulting deep neural network (DNN) models. Much of the literature (with several recent exceptions) of learning with noisy labels focuses on the case when the label noise is independent of features. Practically, annotations errors tend to be instance-dependent and often depend on the difficulty levels of recognizing a certain task. Applying existing results from instance-independent settings would require a significant amount of estimation of noise rates. Therefore, providing theoretically rigorous solutions for learning with instance-dependent label noise remains a challenge. In this paper, we propose CORES$^{2}$ (COnfidence REgularized Sample Sieve), which progressively sieves out corrupted examples. The implementation of CORES$^{2}$ does not require specifying noise rates and yet we are able to provide theoretical guarantees of CORES$^{2}$ in filtering out the corrupted examples. This high-quality sample sieve allows us to treat clean examples and the corrupted ones separately in training a DNN solution, and such a separation is shown to be advantageous in the instance-dependent noise setting. We demonstrate the performance of CORES$^{2}$ on CIFAR10 and CIFAR100 datasets with synthetic instance-dependent label noise and Clothing1M with real-world human noise. As of independent interests, our sample sieve provides a generic machinery for anatomizing noisy datasets and provides a flexible interface for various robust training techniques to further improve the performance. Code is available at
Vin Sachidananda, Ziyi Yang, Chenguang Zhu
Due to widespread interest in machine translation and transfer learning, there are numerous algorithms for mapping multiple embeddings to a shared representation space. Recently, these algorithms have been studied in the setting of bilingual lexicon induction where one seeks to align the embeddings of a source and a target language such that translated word pairs lie close to one another in a common representation space. In this paper, we propose a method, Filtered Inner Product Projection (FIPP), for mapping embeddings to a common representation space. As semantic shifts are pervasive across languages and domains, FIPP first identifies the common geometric structure in both embeddings and then, only on the common structure, aligns the Gram matrices of these embeddings. FIPP is applicable even when the source and target embeddings are of differing dimensionalities. Additionally, FIPP provides computational benefits in ease of implementation and is faster to compute than current approaches. Following the baselines in Glavas et al. 2019, we evaluate FIPP both in the context of bilingual lexicon induction and downstream language tasks. We show that FIPP outperforms existing methods on the XLING BLI dataset for most language pairs while also providing robust performance across downstream tasks.
Sean Fox, Seyedramin Rasoulinezhad, Julian Faraone, david boland, Philip Leong
tl;dr: A new number representation, comparable to recently proposed 8-bit formats, for efficiently training a subset of DNN models.
Training Deep Neural Networks (DNN) with high efficiency can be difficult to achieve with native floating-point representations and commercially available hardware. Specialized arithmetic with custom acceleration offers perhaps the most promising alternative. Ongoing research is trending towards narrow floating-point representations, called minifloats, that pack more operations for a given silicon area and consume less power. In this paper, we introduce Block Minifloat (BM), a new spectrum of minifloat formats capable of training DNNs end-to-end with only 4-8 bit weight, activation and gradient tensors. While standard floating-point representations have two degrees of freedom, via the exponent and mantissa, BM exposes the exponent bias as an additional field for optimization. Crucially, this enables training with fewer exponent bits, yielding dense integer-like hardware for fused multiply-add (FMA) operations. For ResNet trained on ImageNet, 6-bit BM achieves almost no degradation in floating-point accuracy with FMA units that are $4.1\times(23.9\times)$ smaller and consume $2.3\times(16.1\times)$ less energy than FP8 (FP32). Furthermore, our 8-bit BM format matches floating-point accuracy while delivering a higher computational density and faster expected training times.
Myeongjang Pyeon, Jihwan Moon, Taeyoung Hahn, Gunhee Kim
tl;dr: Our approach is the first attempt to automate decoupling neural networks for greedy block-wise learning and outperforms both end-to-end backprop and state-of-the-art greedy-learning methods on CIFAR-10, Tiny-ImageNet and ImageNet classification.
Backward locking and update locking are well-known sources of inefficiency in backpropagation that prevent from concurrently updating layers. Several works have recently suggested using local error signals to train network blocks asynchronously to overcome these limitations. However, they often require numerous iterations of trial-and-error to find the best configuration for local training, including how to decouple network blocks and which auxiliary networks to use for each block. In this work, we propose a differentiable search algorithm named SEDONA to automate this process. Experimental results show that our algorithm can consistently discover transferable decoupled architectures for VGG and ResNet variants, and significantly outperforms the ones trained with end-to-end backpropagation and other state-of-the-art greedy-leaning methods in CIFAR-10, Tiny-ImageNet and ImageNet.
Tianlong Chen, Zhenyu Zhang, Sijia Liu, Shiyu Chang, Zhangyang Wang
tl;dr: Mitigate robust overfitting by properly learned smoothening, establishing the new state-of-the-art bar in adversarial training
A recent study (Rice et al., 2020) revealed overfitting to be a dominant phenomenon in adversarially robust training of deep networks, and that appropriate early-stopping of adversarial training (AT) could match the performance gains of most recent algorithmic improvements. This intriguing problem of robust overfitting motivates us to seek more remedies. As a pilot study, this paper investigates two empirical means to inject more learned smoothening during AT: one leveraging knowledge distillation and self-training to smooth the logits, the other performing stochastic weight averaging (Izmailov et al., 2018) to smooth the weights. Despite the embarrassing simplicity, the two approaches are surprisingly effective and hassle-free in mitigating robust overfitting. Experiments demonstrate that by plugging in them to AT, we can simultaneously boost the standard accuracy by $3.72\%\sim6.68\%$ and robust accuracy by $0.22\%\sim2 .03\%$, across multiple datasets (STL-10, SVHN, CIFAR-10, CIFAR-100, and Tiny ImageNet), perturbation types ($\ell_{\infty}$ and $\ell_2$), and robustified methods (PGD, TRADES, and FSGM), establishing the new state-of-the-art bar in AT. We present systematic visualizations and analyses to dive into their possible working mechanisms. We also carefully exclude the possibility of gradient masking by evaluating our models' robustness against transfer attacks. Codes are available at
Alihan Hüyük, Daniel Jarrett, Cem Tekin, Mihaela van der Schaar
tl;dr: We present a method for learning interpretable representations of behavior to enable auditing, quantifying, and understanding human decision-making processes.
Understanding human behavior from observed data is critical for transparency and accountability in decision-making. Consider real-world settings such as healthcare, in which modeling a decision-maker’s policy is challenging—with no access to underlying states, no knowledge of environment dynamics, and no allowance for live experimentation. We desire learning a data-driven representation of decision- making behavior that (1) inheres transparency by design, (2) accommodates partial observability, and (3) operates completely offline. To satisfy these key criteria, we propose a novel model-based Bayesian method for interpretable policy learning (“Interpole”) that jointly estimates an agent’s (possibly biased) belief-update process together with their (possibly suboptimal) belief-action mapping. Through experiments on both simulated and real-world data for the problem of Alzheimer’s disease diagnosis, we illustrate the potential of our approach as an investigative device for auditing, quantifying, and understanding human decision-making behavior.
Adam Foster, Rattana Pukdee, Tom Rainforth
tl;dr: We propose methods to strengthen the invariance properties of representations obtained by contrastive learning using novel gradient regularization during training and feature averaging at test time.
We propose methods to strengthen the invariance properties of representations obtained by contrastive learning. While existing approaches implicitly induce a degree of invariance as representations are learned, we look to more directly enforce invariance in the encoding process. To this end, we first introduce a training objective for contrastive learning that uses a novel regularizer to control how the representation changes under transformation. We show that representations trained with this objective perform better on downstream tasks and are more robust to the introduction of nuisance transformations at test time. Second, we propose a change to how test time representations are generated by introducing a feature averaging approach that combines encodings from multiple transformations of the original input, finding that this leads to across the board performance gains. Finally, we introduce the novel Spirograph dataset to explore our ideas in the context of a differentiable generative process with multiple downstream tasks, showing that our techniques for learning invariance are highly beneficial.
Tianlong Chen, Zhenyu Zhang, Sijia Liu, Shiyu Chang, Zhangyang Wang
tl;dr: Proposed novel bottom-up lifelong pruning effectively identify the winning tickets, which significantly improve the performance of learning over continual tasks
The lottery ticket hypothesis states that a highly sparsified sub-network can be trained in isolation, given the appropriate weight initialization. This paper extends that hypothesis from one-shot task learning, and demonstrates for the first time that such extremely compact and independently trainable sub-networks can be also identified in the lifelong learning scenario, which we call lifelong tickets. We show that the resulting lifelong ticket can further be leveraged to improve the performance of learning over continual tasks. However, it is highly non-trivial to conduct network pruning in the lifelong setting. Two critical roadblocks arise: i) As many tasks now arrive sequentially, finding tickets in a greedy weight pruning fashion will inevitably suffer from the intrinsic bias, that the earlier emerging tasks impact more; ii) As lifelong learning is consistently challenged by catastrophic forgetting, the compact network capacity of tickets might amplify the risk of forgetting. In view of those, we introduce two pruning options, e.g., top-down and bottom-up, for finding lifelong tickets. Compared to the top-down pruning that extends vanilla (iterative) pruning over sequential tasks, we show that the bottom-up one, which can dynamically shrink and (re-)expand model capacity, effectively avoids the undesirable excessive pruning in the early stage. We additionally introduce lottery teaching that further overcomes forgetting via knowledge distillation aided by external unlabeled data. Unifying those ingredients, we demonstrate the existence of very competitive lifelong tickets, e.g., achieving 3-8% of the dense model size with even higher accuracy, compared to strong class-incremental learning baselines on CIFAR-10/CIFAR-100/Tiny-ImageNet datasets. Codes available at
Jiaqi Yang, Wei Hu, Jason D. Lee, Simon Shaolei Du
tl;dr: We show representation learning provably improves multi-task linear bandits.
We study how representation learning can improve the efficiency of bandit problems. We study the setting where we play $T$ linear bandits with dimension $d$ concurrently, and these $T$ bandit tasks share a common $k (\ll d)$ dimensional linear representation. For the finite-action setting, we present a new algorithm which achieves $\widetilde{O}(T\sqrt{kN} + \sqrt{dkNT})$ regret, where $N$ is the number of rounds we play for each bandit. When $T$ is sufficiently large, our algorithm significantly outperforms the naive algorithm (playing $T$ bandits independently) that achieves $\widetilde{O}(T\sqrt{d N})$ regret. We also provide an $\Omega(T\sqrt{kN} + \sqrt{dkNT})$ regret lower bound, showing that our algorithm is minimax-optimal up to poly-logarithmic factors. Furthermore, we extend our algorithm to the infinite-action setting and obtain a corresponding regret bound which demonstrates the benefit of representation learning in certain regimes. We also present experiments on synthetic and real-world data to illustrate our theoretical findings and demonstrate the effectiveness of our proposed algorithms.
Jesse Vig, Ali Madani, Lav R. Varshney, Caiming Xiong, richard socher, Nazneen Rajani
tl;dr: We analyze the internal representations of protein language models, and show that attention targets structural and functional properties of protein sequences.
Transformer architectures have proven to learn useful representations for protein classification and generation tasks. However, these representations present challenges in interpretability. In this work, we demonstrate a set of methods for analyzing protein Transformer models through the lens of attention. We show that attention: (1) captures the folding structure of proteins, connecting amino acids that are far apart in the underlying sequence, but spatially close in the three-dimensional structure, (2) targets binding sites, a key functional component of proteins, and (3) focuses on progressively more complex biophysical properties with increasing layer depth. We find this behavior to be consistent across three Transformer architectures (BERT, ALBERT, XLNet) and two distinct protein datasets. We also present a three-dimensional visualization of the interaction between attention and protein structure. Code for visualization and analysis is available at
Sebastian Kaltenbach, Phaedon Stelios Koutsourelakis
tl;dr: We propose a novel physics-aware, generative, probabilistic state-space model for learning an effective, lower-dimensional description that can produce long-term predictions.
Given (small amounts of) time-series' data from a high-dimensional, fine-grained, multiscale dynamical system, we propose a generative framework for learning an effective, lower-dimensional, coarse-grained dynamical model that is predictive of the fine-grained system's long-term evolution but also of its behavior under different initial conditions. We target fine-grained models as they arise in physical applications (e.g. molecular dynamics, agent-based models), the dynamics of which are strongly non-stationary but their transition to equilibrium is governed by unknown slow processes which are largely inaccessible by brute-force simulations. Approaches based on domain knowledge heavily rely on physical insight in identifying temporally slow features and fail to enforce the long-term stability of the learned dynamics. On the other hand, purely statistical frameworks lack interpretability and rely on large amounts of expensive simulation data (long and multiple trajectories) as they cannot infuse domain knowledge. The generative framework proposed achieves the aforementioned desiderata by employing a flexible prior on the complex plane for the latent, slow processes, and an intermediate layer of physics-motivated latent variables that reduces reliance on data and imbues inductive bias. In contrast to existing schemes, it does not require the a priori definition of projection operators from the fine-grained description and addresses simultaneously the tasks of dimensionality reduction and model estimation. We demonstrate its efficacy and accuracy in multiscale physical systems of particle dynamics where probabilistic, long-term predictions of phenomena not contained in the training data are produced.
Alvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Suzanne Petryk, Sarah Adel Bargal, Joseph E. Gonzalez
tl;dr: Neural-Backed Decision Trees improve interpretability and accuracy: (1) out-generalize, improve, and match or outperform baseline neural networks; (2) show visual evidence of generalization, reveal ambiguous ImageNet labels, and improve human trust.
Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use. In response, previous work combines decision trees with deep learning, yielding models that (1) sacrifice interpretability for accuracy or (2) sacrifice accuracy for interpretability. We forgo this dilemma by jointly improving accuracy and interpretability using Neural-Backed Decision Trees (NBDTs). NBDTs replace a neural network's final linear layer with a differentiable sequence of decisions and a surrogate loss. This forces the model to learn high-level concepts and lessens reliance on highly-uncertain decisions, yielding (1) accuracy: NBDTs match or outperform modern neural networks on CIFAR, ImageNet and better generalize to unseen classes by up to 16%. Furthermore, our surrogate loss improves the original model's accuracy by up to 2%. NBDTs also afford (2) interpretability: improving human trustby clearly identifying model mistakes and assisting in dataset debugging. Code and pretrained NBDTs are at
Zengyi Qin, Kaiqing Zhang, Yuxiao Chen, Jingkai Chen, Chuchu Fan
tl;dr: We propose a safe and remarkably scalable multi-agent control approach via jointly learning the policy and decentralized control barrier certificates.
We study the multi-agent safe control problem where agents should avoid collisions to static obstacles and collisions with each other while reaching their goals. Our core idea is to learn the multi-agent control policy jointly with learning the control barrier functions as safety certificates. We propose a new joint-learning framework that can be implemented in a decentralized fashion, which can adapt to an arbitrarily large number of agents. Building upon this framework, we further improve the scalability by incorporating neural network architectures that are invariant to the quantity and permutation of neighboring agents. In addition, we propose a new spontaneous policy refinement method to further enforce the certificate condition during testing. We provide extensive experiments to demonstrate that our method significantly outperforms other leading multi-agent control approaches in terms of maintaining safety and completing original tasks. Our approach also shows substantial generalization capability in that the control policy can be trained with 8 agents in one scenario, while being used on other scenarios with up to 1024 agents in complex multi-agent environments and dynamics. Videos and source code can be found at
Jonathan Pilault, Amine El hattami, Christopher Pal
tl;dr: Can multi-task outperform single task fine-tuning? CA-MTL is a new method that shows that it is possible with task conditioned model adaption via a Hypernetwork and uncertainty sampling.
Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and negative task transfer, or learning interference. Often, in Natural Language Processing (NLP), a separate model per task is needed to obtain the best performance. However, many fine-tuning approaches are both parameter inefficient, i.e., potentially involving one new model per task, and highly susceptible to losing knowledge acquired during pretraining. We propose a novel Transformer based Hypernetwork Adapter consisting of a new conditional attention mechanism as well as a set of task-conditioned modules that facilitate weight sharing. Through this construction, we achieve more efficient parameter sharing and mitigate forgetting by keeping half of the weights of a pretrained model fixed. We also use a new multi-task data sampling strategy to mitigate the negative effects of data imbalance across tasks. Using this approach, we are able to surpass single task fine-tuning methods while being parameter and data efficient (using around 66% of the data). Compared to other BERT Large methods on GLUE, our 8-task model surpasses other Adapter methods by 2.8% and our 24-task model outperforms by 0.7-1.0% models that use MTL and single task fine-tuning. We show that a larger variant of our single multi-task model approach performs competitively across 26 NLP tasks and yields state-of-the-art results on a number of test and development sets.
Shengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric I-Chao Chang, Yan Xu
tl;dr: Bridging the gap between between image-conditional and unconditional GAN architectures via co-modulation
Numerous task-specific variants of conditional generative adversarial networks have been developed for image completion. Yet, a serious limitation remains that all existing algorithms tend to fail when handling large-scale missing regions. To overcome this challenge, we propose a generic new approach that bridges the gap between image-conditional and recent modulated unconditional generative architectures via co-modulation of both conditional and stochastic style representations. Also, due to the lack of good quantitative metrics for image completion, we propose the new Paired/Unpaired Inception Discriminative Score (P-IDS/U-IDS), which robustly measures the perceptual fidelity of inpainted images compared to real images via linear separability in a feature space. Experiments demonstrate superior performance in terms of both quality and diversity over state-of-the-art methods in free-form image completion and easy generalization to image-to-image translation. Code is available at
Richard Yuanzhe Pang, He He
Current approaches to text generation largely rely on autoregressive models and maximum likelihood estimation. This paradigm leads to (i) diverse but low-quality samples due to mismatched learning objective and evaluation metric (likelihood vs. quality) and (ii) exposure bias due to mismatched history distributions (gold vs. model-generated). To alleviate these problems, we frame text generation as an offline reinforcement learning (RL) problem with expert demonstrations (i.e., the reference), where the goal is to maximize quality given model-generated histories. We propose GOLD (generation by off-policy learning from demonstrations): an easy-to-optimize algorithm that learns from the demonstrations by importance weighting. Intuitively, GOLD upweights confident tokens and downweights unconfident ones in the reference during training, avoiding optimization issues faced by prior RL approaches that rely on online data collection. According to both automatic and human evaluation, models trained by GOLD outperform those trained by MLE and policy gradient on summarization, question generation, and machine translation. Further, our models are less sensitive to decoding algorithms and alleviate exposure bias.
Yun Kuen Cheung, Yixin Tao
tl;dr: We characterize games in which popular learning algorithms exhibit Lyapunov chaos.
It is of primary interest for ML to understand how agents learn and interact dynamically in competitive environments and games (e.g. GANs). But this has been a difficult task, as irregular behaviors are commonly observed in such systems. This can be explained theoretically, for instance, by the works of Cheung and Piliouras (COLT 2019; NeurIPS 2020), which showed that in two-person zero-sum games, if agents employ one of the most well-known learning algorithms, Multiplicative Weights Update (MWU), then Lyapunov chaos occurs everywhere in the payoff space. In this paper, we study how persistent chaos can occur in the more general normal game settings, where the agents might have the motivation to coordinate (which is not true for zero-sum games) and the number of agents can be arbitrary. We characterize bimatrix games where MWU, its optimistic variant (OMWU) or Follow-the-Regularized-Leader (FTRL) algorithms are Lyapunov chaotic almost everywhere in the payoff space. Technically, our characterization is derived by extending the volume-expansion argument of Cheung and Piliouras via the canonical game decomposition into zero-sum and coordination components. Interestingly, the two components induce opposite volume-changing behaviors, so the overall behavior can be analyzed by comparing the strengths of the components against each other. The comparison is done via our new notion of "matrix domination" or via a linear program. For multi-player games, we present a local equivalence of volume change between general games and graphical games, which is used to perform volume and chaos analyses of MWU and OMWU in potential games.
Danijar Hafner, Timothy P Lillicrap, Mohammad Norouzi, Jimmy Ba
tl;dr: DreamerV2 is the first agent based on a world model to achieve human-level performance on the Atari benchmark.
Intelligent agents need to generalize from past experience to achieve goals in complex environments. World models facilitate such generalization and allow learning behaviors from imagined outcomes to increase sample-efficiency. While learning world models from image inputs has recently become feasible for some tasks, modeling Atari games accurately enough to derive successful behaviors has remained an open challenge for many years. We introduce DreamerV2, a reinforcement learning agent that learns behaviors purely from predictions in the compact latent space of a powerful world model. The world model uses discrete representations and is trained separately from the policy. DreamerV2 constitutes the first agent that achieves human-level performance on the Atari benchmark of 55 tasks by learning behaviors inside a separately trained world model. With the same computational budget and wall-clock time, Dreamer V2 reaches 200M frames and surpasses the final performance of the top single-GPU agents IQN and Rainbow. DreamerV2 is also applicable to tasks with continuous actions, where it learns an accurate world model of a complex humanoid robot and solves stand-up and walking from only pixel inputs.
Kai Yuanqing Xiao, Logan Engstrom, Andrew Ilyas, Aleksander Madry
tl;dr: We develop and use a toolkit to investigate models’ use of (and reliance on) image backgrounds.
We assess the tendency of state-of-the-art object recognition models to depend on signals from image backgrounds. We create a toolkit for disentangling foreground and background signal on ImageNet images, and find that (a) models can achieve non-trivial accuracy by relying on the background alone, (b) models often misclassify images even in the presence of correctly classified foregrounds--up to 88% of the time with adversarially chosen backgrounds, and (c) more accurate models tend to depend on backgrounds less. Our analysis of backgrounds brings us closer to understanding which correlations machine learning models use, and how they determine models' out of distribution performance.
Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont, Julien Mairal
tl;dr: We propose a new, trainable embedding for large sets of features such as biological sequences, and demonstrate its effectiveness.
We address the problem of learning on sets of features, motivated by the need of performing pooling operations in long biological sequences of varying sizes, with long-range dependencies, and possibly few labeled data. To address this challenging task, we introduce a parametrized representation of fixed size, which embeds and then aggregates elements from a given input set according to the optimal transport plan between the set and a trainable reference. Our approach scales to large datasets and allows end-to-end training of the reference, while also providing a simple unsupervised learning mechanism with small computational cost. Our aggregation technique admits two useful interpretations: it may be seen as a mechanism related to attention layers in neural networks, or it may be seen as a scalable surrogate of a classical optimal transport-based kernel. We experimentally demonstrate the effectiveness of our approach on biological sequences, achieving state-of-the-art results for protein fold recognition and detection of chromatin profiles tasks, and, as a proof of concept, we show promising results for processing natural language sequences. We provide an open-source implementation of our embedding that can be used alone or as a module in larger learning models at
Alexander Korotin, Lingxiao Li, Justin Solomon, Evgeny Burnaev
tl;dr: We present a new algorithm to compute Wasserstein-2 barycenters of continuous distributions powered by a straightforward optimization procedure without introducing bias or a generative model.
Wasserstein barycenters provide a geometric notion of the weighted average of probability measures based on optimal transport. In this paper, we present a scalable algorithm to compute Wasserstein-2 barycenters given sample access to the input measures, which are not restricted to being discrete. While past approaches rely on entropic or quadratic regularization, we employ input convex neural networks and cycle-consistency regularization to avoid introducing bias. As a result, our approach does not resort to minimax optimization. We provide theoretical analysis on error bounds as well as empirical evidence of the effectiveness of the proposed approach in low-dimensional qualitative scenarios and high-dimensional quantitative experiments.
Yanzhi Chen, Dinghuai Zhang, Michael U. Gutmann, Aaron Courville, Zhanxing Zhu
tl;dr: We learn low-dimensional near-sufficient statistics for implicit models by infomax principle without estimating the density or even the density ratio.
We consider the fundamental problem of how to automatically construct summary statistics for implicit generative models where the evaluation of the likelihood function is intractable but sampling data from the model is possible. The idea is to frame the task of constructing sufficient statistics as learning mutual information maximizing representations of the data with the help of deep neural networks. The infomax learning procedure does not need to estimate any density or density ratio. We apply our approach to both traditional approximate Bayesian computation and recent neural likelihood methods, boosting their performance on a range of tasks.
George Dasoulas, Johannes F. Lutzeyer, Michalis Vazirgiannis
tl;dr: We propose a parametrised graph shift operator (PGSO) to encode graph structure, providing a unified view of the most common GSOs, and improve GNN performance by incorporating the PGSO into the model training in an end-to-end manner.
In many domains data is currently represented as graphs and therefore, the graph representation of this data becomes increasingly important in machine learning. Network data is, implicitly or explicitly, always represented using a graph shift operator (GSO) with the most common choices being the adjacency, Laplacian matrices and their normalisations. In this paper, a novel parametrised GSO (PGSO) is proposed, where specific parameter values result in the most commonly used GSOs and message-passing operators in graph neural network (GNN) frameworks. The PGSO is suggested as a replacement of the standard GSOs that are used in state-of-the-art GNN architectures and the optimisation of the PGSO parameters is seamlessly included in the model training. It is proved that the PGSO has real eigenvalues and a set of real eigenvectors independent of the parameter values and spectral bounds on the PGSO are derived. PGSO parameters are shown to adapt to the sparsity of the graph structure in a study on stochastic blockmodel networks, where they are found to automatically replicate the GSO regularisation found in the literature. On several real-world datasets the accuracy of state-of-the-art GNN architectures is improved by the inclusion of the PGSO in both node- and graph-classification tasks.
Zongyi Li, Nikola Borislavov Kovachki, Kamyar Azizzadenesheli, Burigede liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
tl;dr: A novel neural operator based on Fourier transformation for learning partial differential equations.
The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural operators that learn mappings between function spaces. For partial differential equations (PDEs), neural operators directly learn the mapping from any functional parametric dependence to the solution. Thus, they learn an entire family of PDEs, in contrast to classical methods which solve one instance of the equation. In this work, we formulate a new neural operator by parameterizing the integral kernel directly in Fourier space, allowing for an expressive and efficient architecture. We perform experiments on Burgers' equation, Darcy flow, and Navier-Stokes equation. The Fourier neural operator is the first ML-based method to successfully model turbulent flows with zero-shot super-resolution. It is up to three orders of magnitude faster compared to traditional PDE solvers. Additionally, it achieves superior accuracy compared to previous learning-based solvers under fixed resolution.
Neil Zeghidour, Olivier Teboul, Félix de Chaumont Quitry, Marco Tagliasacchi
tl;dr: We propose a lightweight learnable frontend of audio that can replace fixed features over a wide range of audio classification tasks.
Mel-filterbanks are fixed, engineered audio features which emulate human perception and have been used through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fundamental limitations of handmade representations. In this work we show that we can train a single learnable frontend that outperforms mel-filterbanks on a wide range of audio signals, including speech, music, audio events and animal sounds, providing a general-purpose learned frontend for audio classification. To do so, we introduce a new principled, lightweight, fully learnable architecture that can be used as a drop-in replacement of mel-filterbanks. Our system learns all operations of audio features extraction, from filtering to pooling, compression and normalization, and can be integrated into any neural network at a negligible parameter cost. We perform multi-task training on eight diverse audio classification tasks, and show consistent improvements of our model over mel-filterbanks and previous learnable alternatives. Moreover, our system outperforms the current state-of-the-art learnable frontend on Audioset, with orders of magnitude fewer parameters.
Angtian Wang, Adam Kortylewski, Alan Yuille
tl;dr: We introduce NeMo, a rendering-based approach to 3D pose estimation that models objects in terms of neural feature activations, instead of image intensities.
3D pose estimation is a challenging but important task in computer vision. In this work, we show that standard deep learning approaches to 3D pose estimation are not robust to partial occlusion. Inspired by the robustness of generative vision models to partial occlusion, we propose to integrate deep neural networks with 3D generative representations of objects into a unified neural architecture that we term NeMo. In particular, NeMo learns a generative model of neural feature activations at each vertex on a dense 3D mesh. Using differentiable rendering we estimate the 3D object pose by minimizing the reconstruction error between NeMo and the feature representation of the target image. To avoid local optima in the reconstruction loss, we train the feature extractor to maximize the distance between the individual feature representations on the mesh using contrastive learning. Our extensive experiments on PASCAL3D+, occluded-PASCAL3D+ and ObjectNet3D show that NeMo is much more robust to partial occlusion compared to standard deep networks, while retaining competitive performance on non-occluded data. Interestingly, our experiments also show that NeMo performs reasonably well even when the mesh representation only crudely approximates the true object geometry with a cuboid, hence revealing that the detailed 3D geometry is not needed for accurate 3D pose estimation.
Noel Loo, Siddharth Swaroop, Richard E Turner
tl;dr: We generalize VCL and Online-EWC and combine with task-specific FiLM layers
Continual learning deals with training models on new tasks and datasets in an online fashion. One strand of research has used probabilistic regularization for continual learning, with two of the main approaches in this vein being Online Elastic Weight Consolidation (Online EWC) and Variational Continual Learning (VCL). VCL employs variational inference, which in other settings has been improved empirically by applying likelihood-tempering. We show that applying this modification to VCL recovers Online EWC as a limiting case, allowing for interpolation between the two approaches. We term the general algorithm Generalized VCL (GVCL). In order to mitigate the observed overpruning effect of VI, we take inspiration from a common multi-task architecture, neural networks with task-specific FiLM layers, and find that this addition leads to significant performance gains, specifically for variational methods. In the small-data regime, GVCL strongly outperforms existing baselines. In larger datasets, GVCL with FiLM layers outperforms or is competitive with existing baselines in terms of accuracy, whilst also providing significantly better calibration.
Robert Dadashi, Leonard Hussenot, Matthieu Geist, Olivier Pietquin
tl;dr: A new Imitation Learning method based on optimal transport.
Imitation Learning (IL) methods seek to match the behavior of an agent with that of an expert. In the present work, we propose a new IL method based on a conceptually simple algorithm: Primal Wasserstein Imitation Learning (PWIL), which ties to the primal form of the Wasserstein distance between the expert and the agent state-action distributions. We present a reward function which is derived offline, as opposed to recent adversarial IL algorithms that learn a reward function through interactions with the environment, and which requires little fine-tuning. We show that we can recover expert behavior on a variety of continuous control tasks of the MuJoCo domain in a sample efficient manner in terms of agent interactions and of expert interactions with the environment. Finally, we show that the behavior of the agent we train matches the behavior of the expert with the Wasserstein distance, rather than the commonly used proxy of performance.
Ruozi Huang, Huang Hu, Wei Wu, Kei Sawada, Mi Zhang, Daxin Jiang
Dancing to music is one of human's innate abilities since ancient times. In machine learning research, however, synthesizing dance movements from music is a challenging problem. Recently, researchers synthesize human motion sequences through autoregressive models like recurrent neural network (RNN). Such an approach often generates short sequences due to an accumulation of prediction errors that are fed back into the neural network. This problem becomes even more severe in the long motion sequence generation. Besides, the consistency between dance and music in terms of style, rhythm and beat is yet to be taken into account during modeling. In this paper, we formalize the music-driven dance generation as a sequence-to-sequence learning problem and devise a novel seq2seq architecture to efficiently process long sequences of music features and capture the fine-grained correspondence between music and dance. Furthermore, we propose a novel curriculum learning strategy to alleviate error accumulation of autoregressive models in long motion sequence generation, which gently changes the training process from a fully guided teacher-forcing scheme using the previous ground-truth movements, towards a less guided autoregressive scheme mostly using the generated movements instead. Extensive experiments show that our approach significantly outperforms the existing state-of-the-arts on automatic metrics and human evaluation. We also make a demo video to demonstrate the superior performance of our proposed approach at
Haotong Qin, Zhongang Cai, Mingyuan Zhang, Yifu Ding, Haiyu Zhao, Shuai Yi, Xianglong Liu, Hao Su
tl;dr: We present BiPointNet, the first model binarization approach to efficient deep learning on point clouds, targeting at extreme compression and acceleration.
To alleviate the resource constraint for real-time point cloud applications that run on edge devices, in this paper we present BiPointNet, the first model binarization approach for efficient deep learning on point clouds. We discover that the immense performance drop of binarized models for point clouds mainly stems from two challenges: aggregation-induced feature homogenization that leads to a degradation of information entropy, and scale distortion that hinders optimization and invalidates scale-sensitive structures. With theoretical justifications and in-depth analysis, our BiPointNet introduces Entropy-Maximizing Aggregation (EMA) to modulate the distribution before aggregation for the maximum information entropy, and Layer-wise Scale Recovery (LSR) to efficiently restore feature representation capacity. Extensive experiments show that BiPointNet outperforms existing binarization methods by convincing margins, at the level even comparable with the full precision counterpart. We highlight that our techniques are generic, guaranteeing significant improvements on various fundamental tasks and mainstream backbones. Moreover, BiPointNet gives an impressive 14.7× speedup and 18.9× storage saving on real-world resource-constrained devices.
Xiangxiang Chu, Xiaoxing Wang, Bo Zhang, Shun Lu, Xiaolin Wei, Junchi Yan
tl;dr: Indicator-free approach to stabilize DARTS
Despite the fast development of differentiable architecture search (DARTS), it suffers from a standing instability issue regarding searching performance, which extremely limits its application. Existing robustifying methods draw clues from the outcome instead of finding out the causing factor. Various indicators such as Hessian eigenvalues are proposed as a signal of performance collapse, and the searching should be stopped once an indicator reaches a preset threshold. However, these methods tend to easily reject good architectures if thresholds are inappropriately set, let alone the searching is intrinsically noisy. In this paper, we undertake a more subtle and direct approach to resolve the collapse. We first demonstrate that skip connections with a learnable architectural coefficient can easily recover from a disadvantageous state and become dominant. We conjecture that skip connections profit too much from this privilege, hence causing the collapse for the derived model. Therefore, we propose to factor out this benefit with an auxiliary skip connection, ensuring a fairer competition for all operations. Extensive experiments on various datasets verify that our approach can substantially improve the robustness of DARTS. Our code is available at
Jongheon Jeong, Jinwoo Shin
tl;dr: We propose a novel discriminator of GAN showing that contrastive representation learning, e.g., SimCLR, and GAN can benefit each other when they are jointly trained.
Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting. It is still unclear, however, that which augmentations could actually improve GANs, and in particular, how to apply a wider range of augmentations in training. In this paper, we propose a novel way to address these questions by incorporating a recent contrastive representation learning scheme into the GAN discriminator, coined ContraD. This "fusion" enables the discriminators to work with much stronger augmentations without increasing their training instability, thereby preventing the discriminator overfitting issue in GANs more effectively. Even better, we observe that the contrastive learning itself also benefits from our GAN training, i.e., by maintaining discriminative features between real and fake samples, suggesting a strong coherence between the two worlds: good contrastive representations are also good for GAN discriminators, and vice versa. Our experimental results show that GANs with ContraD consistently improve FID and IS compared to other recent techniques incorporating data augmentations, still maintaining highly discriminative features in the discriminator in terms of the linear evaluation. Finally, as a byproduct, we also show that our GANs trained in an unsupervised manner (without labels) can induce many conditional generative models via a simple latent sampling, leveraging the learned features of ContraD. Code is available at
Michael Dann, John Thangarajah
tl;dr: In this paper, we identify a problem with value-based deep reinforcement learning that has not previously been investigated -- namely, reward progressivity -- and propose an approach that addresses it via magnitudinal decomposition of the reward.
In this paper we consider reinforcement learning tasks with progressive rewards; that is, tasks where the rewards tend to increase in magnitude over time. We hypothesise that this property may be problematic for value-based deep reinforcement learning agents, particularly if the agent must first succeed in relatively unrewarding regions of the task in order to reach more rewarding regions. To address this issue, we propose Spectral DQN, which decomposes the reward into frequencies such that the high frequencies only activate when large rewards are found. This allows the training loss to be balanced so that it gives more even weighting across small and large reward regions. In two domains with extreme reward progressivity, where standard value-based methods struggle significantly, Spectral DQN is able to make much farther progress. Moreover, when evaluated on a set of six standard Atari games that do not overtly favour the approach, Spectral DQN remains more than competitive: While it underperforms one of the benchmarks in a single game, it comfortably surpasses the benchmarks in three games. These results demonstrate that the approach is not overfit to its target problem, and suggest that Spectral DQN may have advantages beyond addressing reward progressivity.
Nasim Rahaman, Anirudh Goyal, Muhammad Waleed Gondal, Manuel Wuthrich, Stefan Bauer, Yash Sharma, Yoshua Bengio, Bernhard Schölkopf
tl;dr: We model a dynamical system as a collection of recurrent modules that interact according to a spatially informed but learned topology.
Capturing the structure of a data-generating process by means of appropriate inductive biases can help in learning models that generalise well and are robust to changes in the input distribution. While methods that harness spatial and temporal structures find broad application, recent work has demonstrated the potential of models that leverage sparse and modular structure using an ensemble of sparingly interacting modules. In this work, we take a step towards dynamic models that are capable of simultaneously exploiting both modular and spatiotemporal structures. To this end, we model the dynamical system as a collection of autonomous but sparsely interacting sub-systems that interact according to a learned topology which is informed by the spatial structure of the underlying system. This gives rise to a class of models that are well suited for capturing the dynamics of systems that only offer local views into their state, along with corresponding spatial locations of those views. On the tasks of video prediction from cropped frames and multi-agent world modelling from partial observations in the challenging Starcraft2 domain, we find our models to be more robust to the number of available views and better capable of generalisation to novel tasks without additional training than strong baselines that perform equally well or better on the training distribution.
Duy Kien Nguyen, Vedanuj Goswami, Xinlei Chen
tl;dr: 2020 VQA challenge winner; state-of-the-art performance on three counting benchmarks; can work beyond counting towards general visual reasoning
This paper focuses on visual counting, which aims to predict the number of occurrences given a natural image and a query (e.g. a question or a category). Unlike most prior works that use explicit, symbolic models which can be computationally expensive and limited in generalization, we propose a simple and effective alternative by revisiting modulated convolutions that fuse the query and the image locally. Following the design of residual bottleneck, we call our method MoVie, short for Modulated conVolutional bottlenecks. Notably, MoVie reasons implicitly and holistically and only needs a single forward-pass during inference. Nevertheless, MoVie showcases strong performance for counting: 1) advancing the state-of-the-art on counting-specific VQA tasks while being more efficient; 2) outperforming prior-art on difficult benchmarks like COCO for common object counting; 3) helped us secure the first place of 2020 VQA challenge when integrated as a module for ‘number’ related questions in generic VQA models. Finally, we show evidence that modulated convolutions such as MoVie can serve as a general mechanism for reasoning tasks beyond counting.
Yeming Wen, Ghassen Jerfel, Rafael Muller, Michael W Dusenberry, Jasper Snoek, Balaji Lakshminarayanan, Dustin Tran
tl;dr: We found that combining ensembles and data augmentation worsens calibration than applying them individually, and we proposed a simple fix to it.
Ensemble methods which average over multiple neural network predictions are a simple approach to improve a model’s calibration and robustness. Similarly, data augmentation techniques, which encode prior information in the form of invariant feature transformations, are effective for improving calibration and robustness. In this paper, we show a surprising pathology: combining ensembles and data augmentation can harm model calibration. This leads to a trade-off in practice, whereby improved accuracy by combining the two techniques comes at the expense of calibration. On the other hand, selecting only one of the techniques ensures good uncertainty estimates at the expense of accuracy. We investigate this pathology and identify a compounding under-confidence among methods which marginalize over sets of weights and data augmentation techniques which soften labels. Finally, we propose a simple correction, achieving the best of both worlds with significant accuracy and calibration gains over using only ensembles or data augmentation individually. Applying the correction produces new state-of-the art in uncertainty calibration and robustness across CIFAR-10, CIFAR-100, and ImageNet.
Samuel Ritter, Ryan Faulkner, Laurent Sartran, Adam Santoro, Matthew Botvinick, David Raposo
tl;dr: Our agents meta-learn to explore, build models on-the-fly, and plan, enabling them to rapidly solve sequences of tasks in unfamiliar environments.
We propose the challenge of rapid task-solving in novel environments (RTS), wherein an agent must solve a series of tasks as rapidly as possible in an unfamiliar environment. An effective RTS agent must balance between exploring the unfamiliar environment and solving its current task, all while building a model of the new environment over which it can plan when faced with later tasks. While modern deep RL agents exhibit some of these abilities in isolation, none are suitable for the full RTS challenge. To enable progress toward RTS, we introduce two challenge domains: (1) a minimal RTS challenge called the Memory&Planning Game and (2) One-Shot StreetLearn Navigation, which introduces scale and complexity from real-world data. We demonstrate that state-of-the-art deep RL agents fail at RTS in both domains, and that this failure is due to an inability to plan over gathered knowledge. We develop Episodic Planning Networks (EPNs) and show that deep-RL agents with EPNs excel at RTS, outperforming the nearest baseline by factors of 2-3 and learning to navigate held-out StreetLearn maps within a single episode. We show that EPNs learn to execute a value iteration-like planning algorithm and that they generalize to situations beyond their training experience.
Jack Prescott, Xiao Zhang, David Evans
tl;dr: We show that concentration of measure does not prohibit the existence of adversarially robust classifiers using a novel method of empirical concentration estimation.
Concentration of measure has been argued to be the fundamental cause of adversarial vulnerability. Mahloujifar et al. (2019) presented an empirical way to measure the concentration of a data distribution using samples, and employed it to find lower bounds on intrinsic robustness for several benchmark datasets. However, it remains unclear whether these lower bounds are tight enough to provide a useful approximation for the intrinsic robustness of a dataset. To gain a deeper understanding of the concentration of measure phenomenon, we first extend the Gaussian Isoperimetric Inequality to non-spherical Gaussian measures and arbitrary $\ell_p$-norms ($p \geq 2$). We leverage these theoretical insights to design a method that uses half-spaces to estimate the concentration of any empirical dataset under $\ell_p$-norm distance metrics. Our proposed algorithm is more efficient than Mahloujifar et al. (2019)'s, and experiments on synthetic datasets and image benchmarks demonstrate that it is able to find much tighter intrinsic robustness bounds. These tighter estimates provide further evidence that rules out intrinsic dataset concentration as a possible explanation for the adversarial vulnerability of state-of-the-art classifiers.
Jan Hendrik Metzen, Maksym Yatsura
tl;dr: We propose a method for certifying robustness against adversarial patches that combines high certified accuracy with efficient inference while maintaining strong performance on clean data.
Adversarial patches pose a realistic threat model for physical world attacks on autonomous systems via their perception component. Autonomous systems in safety-critical domains such as automated driving should thus contain a fail-safe fallback component that combines certifiable robustness against patches with efficient inference while maintaining high performance on clean inputs. We propose BagCert, a novel combination of model architecture and certification procedure that allows efficient certification. We derive a loss that enables end-to-end optimization of certified robustness against patches of different sizes and locations. On CIFAR10, BagCert certifies 10.000 examples in 43 seconds on a single GPU and obtains 86% clean and 60% certified accuracy against 5x5 patches.
Alon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi, Jonathan Berant
tl;dr: MultiModalQA: A question answering dataset that requires multi-modal multi-hop reasoning over wikipedia text, tables and images, accompanied by a new multi-hop model for tackling the task.
When answering complex questions, people can seamlessly combine information from visual, textual and tabular sources. While interest in models that reason over multiple pieces of evidence has surged in recent years, there has been relatively little work on question answering models that reason across multiple modalities. In this paper, we present MultiModalQA (MMQA): a challenging question answering dataset that requires joint reasoning over text, tables and images. We create MMQA using a new framework for generating complex multi-modal questions at scale, harvesting tables from Wikipedia, and attaching images and text paragraphs using entities that appear in each table. We then define a formal language that allows us to take questions that can be answered from a single modality, and combine them to generate cross-modal questions. Last, crowdsourcing workers take these automatically generated questions and rephrase them into more fluent language. We create 29,918 questions through this procedure, and empirically demonstrate the necessity of a multi-modal multi-hop approach to solve our task: our multi-hop model, ImplicitDecomp, achieves an average F1 of 51.7 over cross-modal questions, substantially outperforming a strong baseline that achieves 38.2 F1, but still lags significantly behind human performance, which is at 90.1 F1.
Yujia Liu, Stefano D'Aronco, Konrad Schindler, Jan Dirk Wegner
tl;dr: An end-to-end trainable deep neural network for converting a 3D point cloud into a wireframe model.
We introduce PC2WF, the first end-to-end trainable deep network architecture to convert a 3D point cloud into a wireframe model. The network takes as input an unordered set of 3D points sampled from the surface of some object, and outputs a wireframe of that object, i.e., a sparse set of corner points linked by line segments. Recovering the wireframe is a challenging task, where the numbers of both vertices and edges are different for every instance, and a-priori unknown. Our architecture gradually builds up the model: It starts by encoding the points into feature vectors. Based on those features, it identifies a pool of candidate vertices, then prunes those candidates to a final set of corner vertices and refines their locations. Next, the corners are linked with an exhaustive set of candidate edges, which is again pruned to obtain the final wireframe. All steps are trainable, and errors can be backpropagated through the entire sequence. We validate the proposed model on a publicly available synthetic dataset, for which the ground truth wireframes are accessible, as well as on a new real-world dataset. Our model produces wireframe abstractions of good quality and outperforms several baselines.
Jonathan Frankle, David J. Schwab, Ari S. Morcos
tl;dr: We study the role and expressive power of learned affine parameters that transform features by freezing all weights at their random initializations and training only BatchNorm.
A wide variety of deep learning techniques from style transfer to multitask learning rely on training affine transformations of features. Most prominent among these is the popular feature normalization technique BatchNorm, which normalizes activations and then subsequently applies a learned affine transform. In this paper, we aim to understand the role and expressive power of affine parameters used to transform features in this way. To isolate the contribution of these parameters from that of the learned features they transform, we investigate the performance achieved when training only these parameters in BatchNorm and freezing all weights at their random initializations. Doing so leads to surprisingly high performance considering the significant limitations that this style of training imposes. For example, sufficiently deep ResNets reach 82% (CIFAR-10) and 32% (ImageNet, top-5) accuracy in this configuration, far higher than when training an equivalent number of randomly chosen parameters elsewhere in the network. BatchNorm achieves this performance in part by naturally learning to disable around a third of the random features. Not only do these results highlight the expressive power of affine parameters in deep learning, but - in a broader sense - they characterize the expressive power of neural networks constructed simply by shifting and rescaling random features.
Johannes Von Oswald, Seijin Kobayashi, Joao Sacramento, Alexander Meulemans, Christian Henning, Benjamin F Grewe
The largely successful method of training neural networks is to learn their weights using some variant of stochastic gradient descent (SGD). Here, we show that the solutions found by SGD can be further improved by ensembling a subset of the weights in late stages of learning. At the end of learning, we obtain back a single model by taking a spatial average in weight space. To avoid incurring increased computational costs, we investigate a family of low-dimensional late-phase weight models which interact multiplicatively with the remaining parameters. Our results show that augmenting standard models with late-phase weights improves generalization in established benchmarks such as CIFAR-10/100, ImageNet and enwik8. These findings are complemented with a theoretical analysis of a noisy quadratic problem which provides a simplified picture of the late phases of neural network learning.
Yunsheng Li, Yinpeng Chen, Xiyang Dai, mengchen liu, Dongdong Chen, Ye Yu, Lu Yuan, Zicheng Liu, Mei Chen, Nuno Vasconcelos
tl;dr: Efficient network with dynamic matrix decomposition
Recent research in dynamic convolution shows substantial performance boost for efficient CNNs, due to the adaptive aggregation of K static convolution kernels. It has two limitations: (a) it increases the number of convolutional weights by K-times, and (b) the joint optimization of dynamic attention and static convolution kernels is challenging. In this paper, we revisit it from a new perspective of matrix decomposition and reveal the key issue is that dynamic convolution applies dynamic attention over channel groups after projecting into a higher dimensional latent space. To address this issue, we propose dynamic channel fusion to replace dynamic attention over channel groups. Dynamic channel fusion not only enables significant dimension reduction of the latent space, but also mitigates the joint optimization difficulty. As a result, our method is easier to train and requires significantly fewer parameters without sacrificing accuracy. Source code is at
Seon-Ho Lee, Chang-Su Kim
tl;dr: A deep clustering algorithm for ordered data is proposed based on the order-identity decomposition.
We propose the deep repulsive clustering (DRC) algorithm of ordered data for effective order learning. First, we develop the order-identity decomposition (ORID) network to divide the information of an object instance into an order-related feature and an identity feature. Then, we group object instances into clusters according to their identity features using a repulsive term. Moreover, we estimate the rank of a test instance, by comparing it with references within the same cluster. Experimental results on facial age estimation, aesthetic score regression, and historical color image classification show that the proposed algorithm can cluster ordered data effectively and also yield excellent rank estimation performance.
Benedikt Boecking, Willie Neiswanger, Eric Xing, Artur Dubrawski
tl;dr: We introduce a framework and method for training classifiers on datasets without ground truth annotation by interacting with domain experts to discover good weak supervision sources.
Obtaining large annotated datasets is critical for training successful machine learning models and it is often a bottleneck in practice. Weak supervision offers a promising alternative for producing labeled datasets without ground truth annotations by generating probabilistic labels using multiple noisy heuristics. This process can scale to large datasets and has demonstrated state of the art performance in diverse domains such as healthcare and e-commerce. One practical issue with learning from user-generated heuristics is that their creation requires creativity, foresight, and domain expertise from those who hand-craft them, a process which can be tedious and subjective. We develop the first framework for interactive weak supervision in which a method proposes heuristics and learns from user feedback given on each proposed heuristic. Our experiments demonstrate that only a small number of feedback iterations are needed to train models that achieve highly competitive test set performance without access to ground truth training labels. We conduct user studies, which show that users are able to effectively provide feedback on heuristics and that test set results track the performance of simulated oracles.
Đorđe Miladinović, Aleksandar Stanić, Stefan Bauer, Jürgen Schmidhuber, Joachim M. Buhmann
tl;dr: A novel neural network layer for improved generative modeling of images, applied to variational autoencoders.
How to improve generative modeling by better exploiting spatial regularities and coherence in images? We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs). In our spatial dependency networks (SDNs), feature maps at each level of a deep neural net are computed in a spatially coherent way, using a sequential gating-based mechanism that distributes contextual information across 2-D space. We show that augmenting the decoder of a hierarchical VAE by spatial dependency layers considerably improves density estimation over baseline convolutional architectures and the state-of-the-art among the models within the same class. Furthermore, we demonstrate that SDN can be applied to large images by synthesizing samples of high quality and coherence. In a vanilla VAE setting, we find that a powerful SDN decoder also improves learning disentangled representations, indicating that neural architectures play an important role in this task. Our results suggest favoring spatial dependency over convolutional layers in various VAE settings. The accompanying source code is given at
Xuxi Chen, Zhenyu Zhang, Yongduo Sui, Tianlong Chen
tl;dr: Winning tickets exist in the deep generative adversarial networks, which substantially outperform previous state-of-the-art compressed GAN
Deep generative adversarial networks (GANs) have gained growing popularity in numerous scenarios, while usually suffer from high parameter complexities for resource-constrained real-world applications. However, the compression of GANs has less been explored. A few works show that heuristically applying compression techniques normally leads to unsatisfactory results, due to the notorious training instability of GANs. In parallel, the lottery ticket hypothesis shows prevailing success on discriminative models, in locating sparse matching subnetworks capable of training in isolation to full model performance. In this work, we for the first time study the existence of such trainable matching subnetworks in deep GANs. For a range of GANs, we certainly find matching subnetworks at $67\%$-$74\%$ sparsity. We observe that with or without pruning discriminator has a minor effect on the existence and quality of matching subnetworks, while the initialization weights used in the discriminator plays a significant role. We then show the powerful transferability of these subnetworks to unseen tasks. Furthermore, extensive experimental results demonstrate that our found subnetworks substantially outperform previous state-of-the-art GAN compression approaches in both image generation (e.g. SNGAN) and image-to-image translation GANs (e.g. CycleGAN). Codes available at
David W Zhang, Gertjan J. Burghouts, Cees G. M. Snoek
tl;dr: A set prediction training and prediction framework that addresses tasks with ambiguous target sets.
Set prediction is about learning to predict a collection of unordered variables with unknown interrelations. Training such models with set losses imposes the structure of a metric space over sets. We focus on stochastic and underdefined cases, where an incorrectly chosen loss function leads to implausible predictions. Example tasks include conditional point-cloud reconstruction and predicting future states of molecules. In this paper we propose an alternative to training via set losses, by viewing learning as conditional density estimation. Our learning framework fits deep energy-based models and approximates the intractable likelihood with gradient-guided sampling. Furthermore, we propose a stochastically augmented prediction algorithm that enables multiple predictions, reflecting the possible variations in the target set. We empirically demonstrate on a variety of datasets the capability to learn multi-modal densities and produce different plausible predictions. Our approach is competitive with previous set prediction models on standard benchmarks. More importantly, it extends the family of addressable tasks beyond those that have unambiguous predictions.
Malik Tiomoko, Hafiz Tiomoko Ali, Romain Couillet
tl;dr: This paper provides a theoretical analysis of Multi Task Learning schemes for large dimensional data
This article provides theoretical insights into the inner workings of multi-task and transfer learning methods, by studying the tractable least-square support vector machine multi-task learning (LS-SVM MTL) method, in the limit of large ($p$) and numerous ($n$) data. By a random matrix analysis applied to a Gaussian mixture data model, the performance of MTL LS-SVM is shown to converge, as $n,p\to\infty$, to a deterministic limit involving simple (small-dimensional) statistics of the data. We prove (i) that the standard MTL LS-SVM algorithm is in general strongly biased and may dramatically fail (to the point that individual single-task LS-SVMs may outperform the MTL approach, even for quite resembling tasks): our analysis provides a simple method to correct these biases, and that we reveal (ii) the sufficient statistics at play in the method, which can be efficiently estimated, even for quite small datasets. The latter result is exploited to automatically optimize the hyperparameters without resorting to any cross-validation procedure. Experiments on popular datasets demonstrate that our improved MTL LS-SVM method is computationally-efficient and outperforms sometimes much more elaborate state-of-the-art multi-task and transfer learning techniques.
Hideaki Hayashi, Seiichi Uchida
tl;dr: A sparse classifier based on a discriminative Gaussian mixture model, which can also be embedded into a neural network.
In probabilistic classification, a discriminative model based on the softmax function has a potential limitation in that it assumes unimodality for each class in the feature space. The mixture model can address this issue, although it leads to an increase in the number of parameters. We propose a sparse classifier based on a discriminative GMM, referred to as a sparse discriminative Gaussian mixture (SDGM). In the SDGM, a GMM-based discriminative model is trained via sparse Bayesian learning. Using this sparse learning framework, we can simultaneously remove redundant Gaussian components and reduce the number of parameters used in the remaining components during learning; this learning method reduces the model complexity, thereby improving the generalization capability. Furthermore, the SDGM can be embedded into neural networks (NNs), such as convolutional NNs, and can be trained in an end-to-end manner. Experimental results demonstrated that the proposed method outperformed the existing softmax-based discriminative models.
Qian Huang, Horace He, Abhay Singh, Ser-Nam Lim, Austin Benson
Graph Neural Networks (GNNs) are a predominant technique for learning over graphs. However, there is relatively little understanding of why GNNs are successful in practice and whether they are necessary for good performance. Here, we show that for many standard transductive node classification benchmarks, we can exceed or match the performance of state-of-the-art GNNs by combining shallow models that ignore the graph structure with two simple post-processing steps that exploit correlation in the label structure: (i) an “error correlation” that spreads residual errors in training data to correct errors in test data and (ii) a “prediction correlation” that smooths the predictions on the test data. We call this overall procedure Correct and Smooth (C&S), and the post-processing steps are implemented via simple modifications to standard label propagation techniques that have long been used in graph-based semi-supervised learning. Our approach exceeds or nearly matches the performance of state-of-the-art GNNs on a wide variety of benchmarks, with just a small fraction of the parameters and orders of magnitude faster runtime. For instance, we exceed the best-known GNN performance on the OGB-Products dataset with 137 times fewer parameters and greater than 100 times less training time. The performance of our methods highlights how directly incorporating label information into the learning algorithm (as is common in traditional methods) yields easy and substantial performance gains. We can also incorporate our techniques into big GNN models, providing modest gains in some cases.
Xuanlin Li, Brandon Trabucco, Dong Huk Park, Michael Luo, Sheng Shen, Trevor Darrell, Yang Gao
tl;dr: The paper proposes an unsupervised learner that discovers non-monotonic autoregressive orders for sequence generation through fully-parallelizable end-to-end training without domain-specific prior.
The predominant approach for language modeling is to encode a sequence of tokens from left to right, but this eliminates a source of information: the order by which the sequence was naturally generated. One strategy to recover this information is to decode both the content and ordering of tokens. Some prior work supervises content and ordering with hand-designed loss functions to encourage specific orders or bootstraps from a predefined ordering. These approaches require domain-specific insight. Other prior work searches over valid insertion operations that lead to ground truth sequences during training, which has high time complexity and cannot be efficiently parallelized. We address these limitations with an unsupervised learner that can be trained in a fully-parallelizable manner to discover high-quality autoregressive orders in a data driven way without a domain-specific prior. The learner is a neural network that performs variational inference with the autoregressive ordering as a latent variable. Since the corresponding variational lower bound is not differentiable, we develop a practical algorithm for end-to-end optimization using policy gradients. Strong empirical results with our solution on sequence modeling tasks suggest that our algorithm is capable of discovering various autoregressive orders for different sequences that are competitive with or even better than fixed orders.
Valerii Iakovlev, Markus Heinonen, Harri Lähdesmäki
tl;dr: The paper introduces a method for learning partial differential equations on arbitrary spatial and temporal grids.
The behavior of many dynamical systems follow complex, yet still unknown partial differential equations (PDEs). While several machine learning methods have been proposed to learn PDEs directly from data, previous methods are limited to discrete-time approximations or make the limiting assumption of the observations arriving at regular grids. We propose a general continuous-time differential model for dynamical systems whose governing equations are parameterized by message passing graph neural networks. The model admits arbitrary space and time discretizations, which removes constraints on the locations of observation points and time intervals between the observations. The model is trained with continuous-time adjoint method enabling efficient neural PDE inference. We demonstrate the model's ability to work with unstructured grids, arbitrary time steps, and noisy observations. We compare our method with existing approaches on several well-known physical systems that involve first and higher-order PDEs with state-of-the-art predictive performance.
Yulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang
tl;dr: We provide a deep understanding of locally supervised learning, and make it perform on par with end-to-end training, while with significantly reduced GPUs memory footprint. Code is available at:
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint. This paper aims to address this problem by revisiting the locally supervised learning, where a network is split into gradient-isolated modules and trained with local supervision. We experimentally show that simply training local modules with E2E loss tends to collapse task-relevant information at early layers, and hence hurts the performance of the full model. To avoid this issue, we propose an information propagation (InfoPro) loss, which encourages local modules to preserve as much useful information as possible, while progressively discard task-irrelevant information. As InfoPro loss is difficult to compute in its original form, we derive a feasible upper bound as a surrogate optimization objective, yielding a simple but effective algorithm. In fact, we show that the proposed method boils down to minimizing the combination of a reconstruction loss and a normal cross-entropy/contrastive term. Extensive empirical results on five datasets (i.e., CIFAR, SVHN, STL-10, ImageNet and Cityscapes) validate that InfoPro is capable of achieving competitive performance with less than 40% memory footprint compared to E2E training, while allowing using training data with higher-resolution or larger batch sizes under the same GPU memory constraint. Our method also enables training local modules asynchronously for potential training acceleration.
Andres Campero, Roberta Raileanu, Heinrich Kuttler, Joshua B. Tenenbaum, Tim Rocktäschel, Edward Grefenstette
tl;dr: A "constructively adversarial" teacher-student setup can augment on-policy algorithms to better solve difficult exploration tasks in RL.
A key challenge for reinforcement learning (RL) consists of learning in environments with sparse extrinsic rewards. In contrast to current RL methods, humans are able to learn new skills with little or no reward by using various forms of intrinsic motivation. We propose AMIGo, a novel agent incorporating -- as form of meta-learning -- a goal-generating teacher that proposes Adversarially Motivated Intrinsic Goals to train a goal-conditioned "student" policy in the absence of (or alongside) environment reward. Specifically, through a simple but effective "constructively adversarial" objective, the teacher learns to propose increasingly challenging -- yet achievable -- goals that allow the student to learn general skills for acting in a new environment, independent of the task to be solved. We show that our method generates a natural curriculum of self-proposed goals which ultimately allows the agent to solve challenging procedurally-generated tasks where other forms of intrinsic motivation and state-of-the-art RL methods fail.
Aviral Kumar, Rishabh Agarwal, Dibya Ghosh, Sergey Levine
tl;dr: Identifies and studies feature matrix rank collapse (i.e. implicit regularization) in deep Q-learning methods.
We identify an implicit under-parameterization phenomenon in value-based deep RL methods that use bootstrapping: when value functions, approximated using deep neural networks, are trained with gradient descent using iterated regression onto target values generated by previous instances of the value network, more gradient updates decrease the expressivity of the current value network. We char- acterize this loss of expressivity via a drop in the rank of the learned value net- work features, and show that this typically corresponds to a performance drop. We demonstrate this phenomenon on Atari and Gym benchmarks, in both offline and online RL settings. We formally analyze this phenomenon and show that it results from a pathological interaction between bootstrapping and gradient-based optimization. We further show that mitigating implicit under-parameterization by controlling rank collapse can improve performance.
Daniel Zügner, Tobias Kirschstein, Michele Catasta, Jure Leskovec, Stephan Günnemann
tl;dr: Language-agnostic learning from Structure and Context of programs improves learning.
Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two complementary representations of the same computer program. Traditionally, designers of machine learning models have relied predominantly either on Structure or Context. We propose a new model, which jointly learns on Context and Structure of source code. In contrast to previous approaches, our model uses only language-agnostic features, i.e., source code and features that can be computed directly from the AST. Besides obtaining state-of-the-art on monolingual code summarization on all five programming languages considered in this work, we propose the first multilingual code summarization model. We show that jointly training on non-parallel data from multiple programming languages improves results on all individual languages, where the strongest gains are on low-resource languages. Remarkably, multilingual training only from Context does not lead to the same improvements, highlighting the benefits of combining Structure and Context for representation learning on code.
Hieu Pham, Xinyi Wang, Yiming Yang, Graham Neubig
tl;dr: Use meta learning to teach the back-translation model to generate better back-translated sentences.
Back-translation is an effective strategy to improve the performance of Neural Machine Translation~(NMT) by generating pseudo-parallel data. However, several recent works have found that better translation quality in the pseudo-parallel data does not necessarily lead to a better final translation model, while lower-quality but diverse data often yields stronger results instead. In this paper we propose a new way to generate pseudo-parallel data for back-translation that directly optimizes the final model performance. Specifically, we propose a meta-learning framework where the back-translation model learns to match the forward-translation model's gradients on the development data with those on the pseudo-parallel data. In our evaluations in both the standard datasets WMT En-De'14 and WMT En-Fr'14, as well as a multilingual translation setting, our method leads to significant improvements over strong baselines.
Yihan Wang, Beining Han, Tonghan Wang, Heng Dong, Chongjie Zhang
tl;dr: We propose an off-policy multi-agent decomposed policy gradient method, addressing the drawbacks that prevent existing multi-agent policy gradient methods from achieving state-of-the-art performance.
Multi-agent policy gradient (MAPG) methods recently witness vigorous progress. However, there is a significant performance discrepancy between MAPG methods and state-of-the-art multi-agent value-based approaches. In this paper, we investigate causes that hinder the performance of MAPG algorithms and present a multi-agent decomposed policy gradient method (DOP). This method introduces the idea of value function decomposition into the multi-agent actor-critic framework. Based on this idea, DOP supports efficient off-policy learning and addresses the issue of centralized-decentralized mismatch and credit assignment in both discrete and continuous action spaces. We formally show that DOP critics have sufficient representational capability to guarantee convergence. In addition, empirical evaluations on the StarCraft II micromanagement benchmark and multi-agent particle environments demonstrate that DOP outperforms both state-of-the-art value-based and policy-based multi-agent reinforcement learning algorithms. Demonstrative videos are available at
Tao Yu, Chien-Sheng Wu, Xi Victoria Lin, bailin wang, Yi Chern Tan, Xinyi Yang, Dragomir Radev, richard socher, Caiming Xiong
tl;dr: Language model pre-training for table semantic parsing.
We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data. We construct synthetic question-SQL pairs over high-quality tables via a synchronous context-free grammar (SCFG). We pre-train our model on the synthetic data to inject important structural properties commonly found in semantic parsing into the pre-training language model. To maintain the model's ability to represent real-world data, we also include masked language modeling (MLM) on several existing table-related datasets to regularize our pre-training process. Our proposed pre-training strategy is much data-efficient. When incorporated with strong base semantic parsers, GraPPa achieves new state-of-the-art results on four popular fully supervised and weakly supervised table semantic parsing tasks.
Alessandro De Palma, Harkirat Behl, Rudy R Bunel, Philip Torr, M. Pawan Kumar
tl;dr: We present a specialised dual solver for a tight ReLU convex relaxation and show that it speeds up formal network verification.
Tight and efficient neural network bounding is of critical importance for the scaling of neural network verification systems. A number of efficient specialised dual solvers for neural network bounds have been presented recently, but they are often too loose to verify more challenging properties. This lack of tightness is linked to the weakness of the employed relaxation, which is usually a linear program of size linear in the number of neurons. While a tighter linear relaxation for piecewise linear activations exists, it comes at the cost of exponentially many constraints and thus currently lacks an efficient customised solver. We alleviate this deficiency via a novel dual algorithm that realises the full potential of the new relaxation by operating on a small active set of dual variables. Our method recovers the strengths of the new relaxation in the dual space: tightness and a linear separation oracle. At the same time, it shares the benefits of previous dual approaches for weaker relaxations: massive parallelism, GPU implementation, low cost per iteration and valid bounds at any time. As a consequence, we obtain better bounds than off-the-shelf solvers in only a fraction of their running time and recover the speed-accuracy trade-offs of looser dual solvers if the computational budget is small. We demonstrate that this results in significant formal verification speed-ups.
Tom Veniat, Ludovic Denoyer, MarcAurelio Ranzato
tl;dr: We propose a new benchmark allowing a detailed analysis of the properties of continual learning alogrithms and a new modular neural network leveraging task-based priors to efficiently learn in the CL setting.
Existing literature in Continual Learning (CL) has focused on overcoming catastrophic forgetting, the inability of the learner to recall how to perform tasks observed in the past. There are however other desirable properties of a CL system, such as the ability to transfer knowledge from previous tasks and to scale memory and compute sub-linearly with the number of tasks. Since most current benchmarks focus only on forgetting using short streams of tasks, we first propose a new suite of benchmarks to probe CL algorithms across these new axes. Finally, we introduce a new modular architecture, whose modules represent atomic skills that can be composed to perform a certain task. Learning a task reduces to figuring out which past modules to re-use, and which new modules to instantiate to solve the current task. Our learning algorithm leverages a task-driven prior over the exponential search space of all possible ways to combine modules, enabling efficient learning on long streams of tasks. Our experiments show that this modular architecture and learning algorithm perform competitively on widely used CL benchmarks while yielding superior performance on the more challenging benchmarks we introduce in this work. The Benchmark is publicly available at
Rishabh Agarwal, Marlos C. Machado, Pablo Samuel Castro, Marc G Bellemare
tl;dr: A contrastive representation learning method which encodes behavioural similarity in RL for improving generalization.
Reinforcement learning methods trained on few environments rarely learn policies that generalize to unseen environments. To improve generalization, we incorporate the inherent sequential structure in reinforcement learning into the representation learning process. This approach is orthogonal to recent approaches, which rarely exploit this structure explicitly. Specifically, we introduce a theoretically motivated policy similarity metric (PSM) for measuring behavioral similarity between states. PSM assigns high similarity to states for which the optimal policies in those states as well as in future states are similar. We also present a contrastive representation learning procedure to embed any state similarity metric, which we instantiate with PSM to obtain policy similarity embeddings (PSEs). We demonstrate that PSEs improve generalization on diverse benchmarks, including LQR with spurious correlations, a jumping task from pixels, and Distracting DM Control Suite.
Haozhi Qi, Xiaolong Wang, Deepak Pathak, Yi Ma, Jitendra Malik
tl;dr: We propose Region Proposal Interaction Networks for physical interaction prediction, which is applied across both simulation and real world environments for long-range prediction and planning.
Learning long-term dynamics models is the key to understanding physical common sense. Most existing approaches on learning dynamics from visual input sidestep long-term predictions by resorting to rapid re-planning with short-term models. This not only requires such models to be super accurate but also limits them only to tasks where an agent can continuously obtain feedback and take action at each step until completion. In this paper, we aim to leverage the ideas from success stories in visual recognition tasks to build object representations that can capture inter-object and object-environment interactions over a long range. To this end, we propose Region Proposal Interaction Networks (RPIN), which reason about each object's trajectory in a latent region-proposal feature space. Thanks to the simple yet effective object representation, our approach outperforms prior methods by a significant margin both in terms of prediction quality and their ability to plan for downstream tasks, and also generalize well to novel environments. Code, pre-trained models, and more visualization results are available at
Jing Yang, Brais Martinez, Adrian Bulat, Georgios Tzimiropoulos
This paper addresses the problem of model compression via knowledge distillation. We advocate for a method that optimizes the output feature of the penultimate layer of the student network and hence is directly related to representation learning. Previous distillation methods which typically impose direct feature matching between the student and the teacher do not take into account the classification problem at hand. On the contrary, our distillation method decouples representation learning and classification and utilizes the teacher's pre-trained classifier to train the student's penultimate layer feature. In particular, for the same input image, we wish the teacher's and student's feature to produce the same output when passed through the teacher's classifier which is achieved with a simple $L_2$ loss. Our method is extremely simple to implement and straightforward to train and is shown to consistently outperform previous state-of-the-art methods over a large set of experimental settings including different (a) network architectures, (b) teacher-student capacities, (c) datasets, and (d) domains. The code will be available at \url{}.
Kanika Madan, Nan Rosemary Ke, Anirudh Goyal, Bernhard Schölkopf, Yoshua Bengio
tl;dr: Different time scale learning of independent mechanisms can lead to a better generalization.
Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel combinations of existing pieces of knowledge. We hypothesize that such a decomposition of knowledge is particularly relevant for being able to generalize in a systematic way to out-of-distribution changes. To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs and its reward function are stationary and can be re-used across tasks. An attention mechanism dynamically selects which modules can be adapted to the current task, and the parameters of the \textit{selected} modules are allowed to change quickly as the learner is confronted with variations in what it experiences, while the parameters of the attention mechanisms act as stable, slowly changing, meta-parameters. We focus on pieces of knowledge captured by an ensemble of modules sparsely communicating with each other via a bottleneck of attention. We find that meta-learning the modular aspects of the proposed system greatly helps in achieving faster adaptation in a reinforcement learning setup involving navigation in a partially observed grid world with image-level input. We also find that reversing the role of parameters and meta-parameters does not work nearly as well, suggesting a particular role for fast adaptation of the dynamically selected modules.
Marisa Kirisame, Steven Lyubomirsky, Altan Haan, Jennifer Brennan, Mike He, Jared Roesch, Tianqi Chen, Zachary Tatlock
tl;dr: We present an online algorithm for rematerialization (recomputing intermediate activations during backpropagation instead of storing them), which enables training under low memory, finding that it is competitive with offline techniques.
Checkpointing enables the training of deep learning models under restricted memory budgets by freeing intermediate activations from memory and recomputing them on demand. Current checkpointing techniques statically plan these recomputations offline and assume static computation graphs. We demonstrate that a simple online algorithm can achieve comparable performance by introducing Dynamic Tensor Rematerialization (DTR), a greedy online algorithm for checkpointing that is extensible and general, is parameterized by eviction policy, and supports dynamic models. We prove that DTR can train an $N$-layer linear feedforward network on an $\Omega(\sqrt{N})$ memory budget with only $\mathcal{O}(N)$ tensor operations. DTR closely matches the performance of optimal static checkpointing in simulated experiments. We incorporate a DTR prototype into PyTorch merely by interposing on tensor allocations and operator calls and collecting lightweight metadata on tensors.
Zeyuan Allen-Zhu, Faeze Ebrahimianghazani, Jerry Li, Dan Alistarh
tl;dr: New algorithm for non-convex distributed optimization against Byzantine attacks, with strong theoretical guarantees, and improves on the performance of prior methods for training deep neural networks against Byzantine attacks.
We study adversary-resilient stochastic distributed optimization, in which $m$ machines can independently compute stochastic gradients, and cooperate to jointly optimize over their local objective functions. However, an $\alpha$-fraction of the machines are Byzantine, in that they may behave in arbitrary, adversarial ways. We consider a variant of this procedure in the challenging non-convex case. Our main result is a new algorithm SafeguardSGD, which can provably escape saddle points and find approximate local minima of the non-convex objective. The algorithm is based on a new concentration filtering technique, and its sample and time complexity bounds match the best known theoretical bounds in the stochastic, distributed setting when no Byzantine machines are present. Our algorithm is very practical: it improves upon the performance of all prior methods when training deep neural networks, it is relatively lightweight, and it is the first method to withstand two recently-proposed Byzantine attacks.
Guoqing Liu, Chuheng Zhang, Li Zhao, Tao Qin, Jinhua Zhu, Li Jian, Nenghai Yu, Tie-Yan Liu
tl;dr: We propose a novel contrastive learning based auxiliary task which forces the learnt representations to discriminate state-action pairs with different returns and achieve superior performance on complex tasks in terms of sample effiency.
Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems into consideration and are unsupervised. By leveraging returns, the most important feedback signals in RL, we propose a novel auxiliary task that forces the learnt representations to discriminate state-action pairs with different returns. Our auxiliary loss is theoretically justified to learn representations that capture the structure of a new form of state-action abstraction, under which state-action pairs with similar return distributions are aggregated together. Empirically, our algorithm outperforms strong baselines on complex tasks in Atari games and DeepMind Control suite, and achieves even better performance when combined with existing auxiliary tasks.
Alberto Bernacchia
tl;dr: We show theoretically that the optimal inner learning rate of MAML during training is always negative in a family of models
Deep learning models require a large amount of data to perform well. When data is scarce for a target task, we can transfer the knowledge gained by training on similar tasks to quickly learn the target. A successful approach is meta-learning, or "learning to learn" a distribution of tasks, where "learning" is represented by an outer loop, and "to learn" by an inner loop of gradient descent. However, a number of recent empirical studies argue that the inner loop is unnecessary and more simple models work equally well or even better. We study the performance of MAML as a function of the learning rate of the inner loop, where zero learning rate implies that there is no inner loop. Using random matrix theory and exact solutions of linear models, we calculate an algebraic expression for the test loss of MAML applied to mixed linear regression and nonlinear regression with overparameterized models. Surprisingly, while the optimal learning rate for adaptation is positive, we find that the optimal learning rate for training is always negative, a setting that has never been considered before. Therefore, not only does the performance increase by decreasing the learning rate to zero, as suggested by recent work, but it can be increased even further by decreasing the learning rate to negative values. These results help clarify under what circumstances meta-learning performs best.
Sana Tonekaboni, Danny Eytan, Anna Goldenberg
tl;dr: An unsupervised representation learning framework for high-dimensional non-stationary time series
Time series are often complex and rich in information but sparsely labeled and therefore challenging to model. In this paper, we propose a self-supervised framework for learning robust and generalizable representations for time series. Our approach, called Temporal Neighborhood Coding (TNC), takes advantage of the local smoothness of a signal's generative process to define neighborhoods in time with stationary properties. Using a debiased contrastive objective, our framework learns time series representations by ensuring that in the encoding space, the distribution of signals from within a neighborhood is distinguishable from the distribution of non-neighboring signals. Our motivation stems from the medical field, where the ability to model the dynamic nature of time series data is especially valuable for identifying, tracking, and predicting the underlying patients' latent states in settings where labeling data is practically impossible. We compare our method to recently developed unsupervised representation learning approaches and demonstrate superior performance on clustering and classification tasks for multiple datasets.
Judy Borowski, Roland Simon Zimmermann, Judith Schepers, Robert Geirhos, Thomas S. A. Wallis, Matthias Bethge, Wieland Brendel
tl;dr: Using human psychophysical experiments, we show that natural images can be significantly more informative for interpreting neural network activations than a state-of-the-art synthetic feature visualization.
Feature visualizations such as synthetic maximally activating images are a widely used explanation method to better understand the information processing of convolutional neural networks (CNNs). At the same time, there are concerns that these visualizations might not accurately represent CNNs' inner workings. Here, we measure how much extremely activating images help humans to predict CNN activations. Using a well-controlled psychophysical paradigm, we compare the informativeness of synthetic images by Olah et al. (2017) with a simple baseline visualization, namely exemplary natural images that also strongly activate a specific feature map. Given either synthetic or natural reference images, human participants choose which of two query images leads to strong positive activation. The experiment is designed to maximize participants' performance, and is the first to probe intermediate instead of final layer representations. We find that synthetic images indeed provide helpful information about feature map activations ($82\pm4\%$ accuracy; chance would be $50\%$). However, natural images --- originally intended to be a baseline --- outperform these synthetic images by a wide margin ($92\pm2\%$). Additionally, participants are faster and more confident for natural images, whereas subjective impressions about the interpretability of the feature visualizations by Olah et al. (2017) are mixed. The higher informativeness of natural images holds across most layers, for both expert and lay participants as well as for hand- and randomly-picked feature visualizations. Even if only a single reference image is given, synthetic images provide less information than natural images ($65\pm5\%$ vs. $73\pm4\%$). In summary, synthetic images from a popular feature visualization method are significantly less informative for assessing CNN activations than natural images. We argue that visualization methods should improve over this simple baseline.
Hao Zhang, Sen Li, YinChao Ma, Mingjie Li, Yichen Xie, Quanshi Zhang
tl;dr: We prove and improve the utility of the dropout operation from a game-theoretic view.
This paper aims to understand and improve the utility of the dropout operation from the perspective of game-theoretical interactions. We prove that dropout can suppress the strength of interactions between input variables of deep neural networks (DNNs). The theoretical proof is also verified by various experiments. Furthermore, we find that such interactions were strongly related to the over-fitting problem in deep learning. So, the utility of dropout can be regarded as decreasing interactions to alleviating the significance of over-fitting. Based on this understanding, we propose the interaction loss to further improve the utility of dropout. Experimenta