Publications

Discovering Object-Centric Generalized Value Functions From Pixels
Somjit Nath
Gopeshh Raaj Subbaraj
Khimya Khetarpal
Samira Ebrahimi Kahou
Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using ha… (voir plus)nd-crafted auxiliary tasks and pseudo rewards. Automatically learning such representations in an object-centric manner geared towards control and fast adaptation remains an open research problem. In this paper, we introduce a method that tries to discover meaningful features from objects, translating them to temporally coherent "question" functions and leveraging the subsequent learned general value functions for control. We compare our approach with state-of-the-art techniques alongside other ablations and show competitive performance in both stationary and non-stationary settings. Finally, we also investigate the discovered general value functions and through qualitative analysis show that the learned representations are not only interpretable but also, centered around objects that are invariant to changes across tasks facilitating fast adaptation.
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Discrete Key-Value Bottleneck
Frederik Träuble
Anirudh Goyal
Nasim Rahaman
Michael Mozer
Kenji Kawaguchi
Yoshua Bengio
Bernhard Schölkopf
Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with… (voir plus) non-stationary training data streams such as continual learning. One powerful approach that has addressed this challenge involves pre-training of large encoders on volumes of readily available data, followed by task-specific tuning. Given a new task, however, updating the weights of these encoders is challenging as a large number of weights needs to be fine-tuned, and as a result, they forget information about the previous tasks. In the present work, we propose a model architecture to address this issue, building upon a discrete bottleneck containing pairs of separate and learnable key-value codes. Our paradigm will be to encode; process the representation via a discrete bottleneck; and decode. Here, the input is fed to the pre-trained encoder, the output of the encoder is used to select the nearest keys, and the corresponding values are fed to the decoder to solve the current task. The model can only fetch and re-use a sparse number of these key-value pairs during inference, enabling localized and context-dependent model updates. We theoretically investigate the ability of the discrete key-value bottleneck to minimize the effect of learning under distribution shifts and show that it reduces the complexity of the hypothesis class. We empirically verify the proposed method under challenging class-incremental learning scenarios and show that the proposed model - without any task boundaries - reduces catastrophic forgetting across a wide variety of pre-trained models, outperforming relevant baselines on this task.
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Equivariance with Learned Canonicalization Functions
Sékou-Oumar Kaba
Arnab Kumar Mondal
Yan Zhang
Yoshua Bengio
Siamak Ravanbakhsh
Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations… (voir plus). In this paper, we propose an alternative that avoids this architectural constraint by learning to produce canonical representations of the data. These canonicalization functions can readily be plugged into non-equivariant backbone architectures. We offer explicit ways to implement them for some groups of interest. We show that this approach enjoys universality while providing interpretable insights. Our main hypothesis, supported by our empirical results, is that learning a small neural network to perform canonicalization is better than using predefined heuristics. Our experiments show that learning the canonicalization function is competitive with existing techniques for learning equivariant functions across many tasks, including image classification,
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
FAENet: Frame Averaging Equivariant GNN for Materials Modeling
Alexandre Duval
Victor Schmidt
Alex Hernandez Garcia
Santiago Miret
Fragkiskos D. Malliaros
Yoshua Bengio
David Rolnick
Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to speci… (voir plus)fic symmetries. While graph neural networks (GNNs) have proven successful in such tasks, they enforce symmetries via the model architecture, which often reduces their expressivity, scalability and comprehensibility. In this paper, we introduce (1) a flexible framework relying on stochastic frame-averaging (SFA) to make any model E(3)-equivariant or invariant through data transformations. (2) FAENet: a simple, fast and expressive GNN, optimized for SFA, that processes geometric information without any symmetrypreserving design constraints. We prove the validity of our method theoretically and empirically demonstrate its superior accuracy and computational scalability in materials modeling on the OC20 dataset (S2EF, IS2RE) as well as common molecular modeling tasks (QM9, QM7-X). A package implementation is available at https://faenet.readthedocs.io.
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Flexible Phase Dynamics for Bio-Plausible Contrastive Learning
Ezekiel Williams
Colin Bredenberg
Guillaume Lajoie
Many learning algorithms used as normative models in neuroscience or as candidate approaches for learning on neuromorphic chips learn by con… (voir plus)trasting one set of network states with another. These Contrastive Learning (CL) algorithms are traditionally implemented with rigid, temporally non-local, and periodic learning dynamics that could limit the range of physical systems capable of harnessing CL. In this study, we build on recent work exploring how CL might be implemented by biological or neurmorphic systems and show that this form of learning can be made temporally local, and can still function even if many of the dynamical requirements of standard training procedures are relaxed. Thanks to a set of general theorems corroborated by numerical experiments across several CL models, our results provide theoretical foundations for the study and development of CL methods for biological and neuromorphic neural networks.
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
GFlowNet-EM for Learning Compositional Latent Variable Models
Edward J. Hu
Nikolay Malkin
Moksh Jain
Katie Everett
Alexandros Graikos
Yoshua Bengio
Latent variable models (LVMs) with discrete compositional latents are an important but challenging setting due to a combinatorially large nu… (voir plus)mber of possible configurations of the latents. A key tradeoff in modeling the posteriors over latents is between expressivity and tractable optimization. For algorithms based on expectation-maximization (EM), the E-step is often intractable without restrictive approximations to the posterior. We propose the use of GFlowNets, algorithms for sampling from an unnormalized density by learning a stochastic policy for sequential construction of samples, for this intractable E-step. By training GFlowNets to sample from the posterior over latents, we take advantage of their strengths as amortized variational inference algorithms for complex distributions over discrete structures. Our approach, GFlowNet-EM, enables the training of expressive LVMs with discrete compositional latents, as shown by experiments on non-context-free grammar induction and on images using discrete variational autoencoders (VAEs) without conditional independence enforced in the encoder.
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
Shengchao Liu
Weitao Du
Zhiming Ma
Hongyu Guo
Jian Tang
Molecule pretraining has quickly become the go-to schema to boost the performance of AI-based drug discovery. Naturally, molecules can be re… (voir plus)presented as 2D topological graphs or 3D geometric point clouds. Although most existing pertaining methods focus on merely the single modality, recent research has shown that maximizing the mutual information (MI) between such two modalities enhances the molecule representation ability. Meanwhile, existing molecule multi-modal pretraining approaches approximate MI based on the representation space encoded from the topology and geometry, thus resulting in the loss of critical structural information of molecules. To address this issue, we propose MoleculeSDE. MoleculeSDE leverages group symmetric (e.g., SE(3)-equivariant and reflection-antisymmetric) stochastic differential equation models to generate the 3D geometries from 2D topologies, and vice versa, directly in the input space. It not only obtains tighter MI bound but also enables prosperous downstream tasks than the previous work. By comparing with 17 pretraining baselines, we empirically verify that MoleculeSDE can learn an expressive representation with state-of-the-art performance on 26 out of 32 downstream tasks.
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Guided-topic modelling of single-cell transcriptomes enables sub-cell-type and disease-subtype deconvolution of bulk transcriptomes
Lakshmipuram Seshadri Swapna
Michael Huang
Yuemei Li
Cell-type composition is an important indicator of health. We present Guided Topic Model for deconvolution (GTM-decon) to automatically infe… (voir plus)r cell-type-specific gene topic distributions from single-cell RNA-seq data for deconvolving bulk transcriptomes. GTM-decon performs competitively on deconvolving simulated and real bulk data compared with the state-of-the-art methods. Moreover, as demonstrated in deconvolving disease transcriptomes, GTM-decon can infer multiple cell-type-specific gene topic distributions per cell type, which captures sub-cell-type variations. GTM-decon can also use phenotype labels from single-cell or bulk data as a guide to infer phenotype-specific gene distributions. In a nested-guided design, GTM-decon identified cell-type-specific differentially expressed genes from bulk breast cancer transcriptomes.
2023-07-02
bioRxiv (prépublication)
doi.org
Hidden Symmetries of ReLU Networks
J. Elisenda Grigsby
J. Elisenda Grigsby
Kathryn Lindsey
David Rolnick
The parameter space for any fixed architecture of feedforward ReLU neural networks serves as a proxy during training for the associated clas… (voir plus)s of functions - but how faithful is this representation? It is known that many different parameter settings can determine the same function. Moreover, the degree of this redundancy is inhomogeneous: for some networks, the only symmetries are permutation of neurons in a layer and positive scaling of parameters at a neuron, while other networks admit additional hidden symmetries. In this work, we prove that, for any network architecture where no layer is narrower than the input, there exist parameter settings with no hidden symmetries. We also describe a number of mechanisms through which hidden symmetries can arise, and empirically approximate the functional dimension of different network architectures at initialization. These experiments indicate that the probability that a network has no hidden symmetries decreases towards 0 as depth increases, while increasing towards 1 as width and input dimension increase.
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
Abdurakhmon Sadiev
Marina Danilova
Eduard Gorbunov
Samuel Horváth
Gauthier Gidel
Pavel Dvurechensky
Alexander Gasnikov
Peter Richtárik
During the recent years the interest of optimization and machine learning communities in high-probability convergence of stochastic optimiza… (voir plus)tion methods has been growing. One of the main reasons for this is that high-probability complexity bounds are more accurate and less studied than in-expectation ones. However, SOTA high-probability non-asymptotic convergence results are derived under strong assumptions such as boundedness of the gradient noise variance or of the objective’s gradient itself. In this paper, we propose several algorithms with high-probability convergence results under less restrictive assumptions. In particular, we derive new high-probability convergence results under the assumption that the gradient/operator noise has bounded central
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Maximal Initial Learning Rates in Deep ReLU Networks
Gaurav Iyer
Boris Hanin
David Rolnick
Training a neural network requires choosing a suitable learning rate, which involves a trade-off between speed and effectiveness of converge… (voir plus)nce. While there has been considerable theoretical and empirical analysis of how large the learning rate can be, most prior work focuses only on late-stage training. In this work, we introduce the maximal initial learning rate
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Mechanistic Mode Connectivity
Ekdeep Singh Lubana
Eric J Bigelow
Robert P. Dick
David M. Krueger
Hidenori Tanaka
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press