Portrait of Yoshua Bengio

Yoshua Bengio

Core Academic Member
Canada CIFAR AI Chair
Full Professor, Université de Montréal, Department of Computer Science and Operations Research Department
Founder and Scientific Advisor, Leadership Team
Research Topics
Causality
Computational Neuroscience
Deep Learning
Generative Models
Graph Neural Networks
Machine Learning Theory
Medical Machine Learning
Molecular Modeling
Natural Language Processing
Probabilistic Models
Reasoning
Recurrent Neural Networks
Reinforcement Learning
Representation Learning

Biography

*For media requests, please write to medias@mila.quebec.

For more information please contact Marie-Josée Beauchamp, Administrative Assistant at marie-josee.beauchamp@mila.quebec.

Yoshua Bengio is recognized worldwide as a leading expert in AI. He is most known for his pioneering work in deep learning, which earned him the 2018 A.M. Turing Award, “the Nobel Prize of computing,” with Geoffrey Hinton and Yann LeCun.

Bengio is a full professor at Université de Montréal, and the founder and scientific advisor of Mila – Quebec Artificial Intelligence Institute. He is also a senior fellow at CIFAR and co-directs its Learning in Machines & Brains program, serves as special advisor and founding scientific director of IVADO, and holds a Canada CIFAR AI Chair.

In 2019, Bengio was awarded the prestigious Killam Prize and in 2022, he was the most cited computer scientist in the world by h-index. He is a Fellow of the Royal Society of London, Fellow of the Royal Society of Canada, Knight of the Legion of Honor of France and Officer of the Order of Canada. In 2023, he was appointed to the UN’s Scientific Advisory Board for Independent Advice on Breakthroughs in Science and Technology.

Concerned about the social impact of AI, Bengio helped draft the Montréal Declaration for the Responsible Development of Artificial Intelligence and continues to raise awareness about the importance of mitigating the potentially catastrophic risks associated with future AI systems.

Current Students

Collaborating Alumni - McGill University
Collaborating Alumni - Université de Montréal
Collaborating researcher - Cambridge University
Principal supervisor :
PhD - Université de Montréal
Independent visiting researcher
Co-supervisor :
PhD - Université de Montréal
Collaborating researcher - N/A
Principal supervisor :
PhD - Université de Montréal
Collaborating researcher - KAIST
PhD - Université de Montréal
PhD - Université de Montréal
Research Intern - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
PhD - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
Research Intern - Université de Montréal
PhD - Université de Montréal
PhD - Université de Montréal
Principal supervisor :
Research Intern - Université de Montréal
Postdoctorate - Université de Montréal
Principal supervisor :
Collaborating researcher - Université de Montréal
Collaborating Alumni - Université de Montréal
Postdoctorate - Université de Montréal
Principal supervisor :
Collaborating Alumni - Université de Montréal
Collaborating Alumni
Collaborating Alumni - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Collaborating Alumni - Université de Montréal
PhD - Université de Montréal
Co-supervisor :
Collaborating researcher - Université de Montréal
PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Principal supervisor :
Postdoctorate - Université de Montréal
Principal supervisor :
Independent visiting researcher - Université de Montréal
PhD - Université de Montréal
Principal supervisor :
Collaborating researcher - Ying Wu Coll of Computing
PhD - University of Waterloo
Principal supervisor :
Collaborating Alumni - Max-Planck-Institute for Intelligent Systems
PhD - Université de Montréal
Postdoctorate - Université de Montréal
Independent visiting researcher - Université de Montréal
Postdoctorate - Université de Montréal
PhD - Université de Montréal
Principal supervisor :
Collaborating Alumni - Université de Montréal
Postdoctorate - Université de Montréal
Master's Research - Université de Montréal
Collaborating Alumni - Université de Montréal
Master's Research - Université de Montréal
Postdoctorate
Independent visiting researcher - Technical University of Munich
PhD - Université de Montréal
Co-supervisor :
Postdoctorate - Université de Montréal
Postdoctorate - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
Principal supervisor :
Collaborating researcher - Université de Montréal
Collaborating researcher
Collaborating researcher - KAIST
PhD - McGill University
Principal supervisor :
PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
PhD - McGill University
Principal supervisor :

Publications

Learning Long-term Dependencies Using Cognitive Inductive Biases in Self-attention RNNs
Giancarlo Kerg
Bhargav Kanuparthi
Anirudh Goyal
Kyle Goyette
Attention and self-attention mechanisms, inspired by cognitive processes, are now central to state-of-the-art deep learning on sequential ta… (see more)sks. However, most recent progress hinges on heuristic approaches that rely on considerable memory and computational resources that scale poorly. In this work, we propose a relevancy screening mechanism, inspired by the cognitive process of memory consolidation, that allows for a scalable use of sparse self-attention with recurrence. We use simple numerical experiments to demonstrate that this mechanism helps enable recurrent systems on generalization and transfer learning tasks. Based on our results, we propose a concrete direction of research to improve scalability and generalization of attentive recurrent networks.
Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
Sai Krishna Gottipati
B. Sattarov
Sufeng Niu
Yashaswi Pathak
Haoran Wei
Shengchao Liu
Karam M. J. Thomas
Simon R. Blackburn
Connor Wilson. Coley
Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep gen… (see more)erative models. However, current generative approaches exhibit a significant challenge as they do not ensure that the proposed molecular structures can be feasibly synthesized nor do they provide the synthesis routes of the proposed small molecules, thereby seriously limiting their practical applicability. In this work, we propose a novel forward synthesis framework powered by reinforcement learning (RL) for de novo drug design, Policy Gradient for Forward Synthesis (PGFS), that addresses this challenge by embedding the concept of synthetic accessibility directly into the de novo drug design system. In this setup, the agent learns to navigate through the immense synthetically accessible chemical space by subjecting commercially available small molecule building blocks to valid chemical reactions at every time step of the iterative virtual multi-step synthesis process. The proposed environment for drug discovery provides a highly challenging test-bed for RL algorithms owing to the large state space and high-dimensional continuous action space with hierarchical actions. PGFS achieves state-of-the-art performance in generating structures with high QED and penalized clogP. Moreover, we validate PGFS in an in-silico proof-of-concept associated with three HIV targets. Finally, we describe how the end-to-end training conceptualized in this study represents an important paradigm in radically expanding the synthesizable chemical space and automating the drug discovery process.
Learning the Arrow of Time for Problems in Reinforcement Learning.
Nasim Rahaman
Steffen Wolf
Anirudh Goyal
Roman Remme
Meta Attention Networks: Meta Learning Attention To Modulate Information Between Sparsely Interacting Recurrent Modules
Kanika Madan
Nan Rosemary Ke
Anirudh Goyal
Decomposing knowledge into interchangeable pieces promises a generalization advantage when, at some level of representation, the learner is … (see more)likely to be faced with situations requiring novel combinations of existing pieces of knowledge or computation. We hypothesize that such a decomposition of knowledge is particularly relevant for higher levels of representation as we see this at work in human cognition and natural language in the form of systematicity or systematic generalization. To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs, as well as its reward function are stationary and can be re-used across tasks and changes in distribution. As the learner is confronted with variations in experiences, the attention selects which modules should be adapted and the parameters of those selected modules are adapted fast, while the parameters of attention mechanisms are updated slowly as meta-parameters. We find that both the meta-learning and the modular aspects of the proposed system greatly help achieve faster learning in experiments with reinforcement learning setup involving navigation in a partially observed grid world.
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Tristan Deleu
Nasim Rahaman
Nan Rosemary Ke
Sébastien Lachapelle
Olexa Bilaniuk
Anirudh Goyal
We propose to meta-learn causal structures based on how fast a learner adapts to new distributions arising from sparse distributional change… (see more)s, e.g. due to interventions, actions of agents and other sources of non-stationarities. We show that under this assumption, the correct causal structural choices lead to faster adaptation to modified distributions because the changes are concentrated in one or just a few mechanisms when the learned knowledge is modularized appropriately. This leads to sparse expected gradients and a lower effective number of degrees of freedom needing to be relearned while adapting to the change. It motivates using the speed of adaptation to a modified distribution as a meta-learning objective. We demonstrate how this can be used to determine the cause-effect relationship between two observed variables. The distributional changes do not need to correspond to standard interventions (clamping a variable), and the learner has no direct knowledge of these interventions. We show that causal structures can be parameterized via continuous variables and learned end-to-end. We then explore how these ideas could be used to also learn an encoder that would map low-level observed variables to unobserved causal variables leading to faster adaptation out-of-distribution, learning a representation space where one can satisfy the assumptions of independent mechanisms and of small and sparse changes in these mechanisms due to actions and non-stationarities.
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
Boris Oreshkin
Dmitri Carpov
We focus on solving the univariate times series point forecasting problem using deep learning. We propose a deep neural architecture based o… (see more)n backward and forward residual links and a very deep stack of fully-connected layers. The architecture has a number of desirable properties, being interpretable, applicable without modification to a wide array of target domains, and fast to train. We test the proposed architecture on several well-known datasets, including M3, M4 and TOURISM competition datasets containing time series from diverse domains. We demonstrate state-of-the-art performance for two configurations of N-BEATS for all the datasets, improving forecast accuracy by 11% over a statistical benchmark and by 3% over last year's winner of the M4 competition, a domain-adjusted hand-crafted hybrid between neural network and statistical time series models. The first configuration of our model does not employ any time-series-specific components and its performance on heterogeneous datasets strongly suggests that, contrarily to received wisdom, deep learning primitives such as residual blocks are by themselves sufficient to solve a wide range of forecasting problems. Finally, we demonstrate how the proposed architecture can be augmented to provide outputs that are interpretable without considerable loss in accuracy.
PAST DSAA KEYNOTE SPEAKERS
An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs. By utilizing fas… (see more)t matrix block-approximation techniques, we propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions, while being able to meaningfully model local information of the graph (e.g., degrees) as well as global information (e.g., clustering coefficient, assortativity, etc.) if desired. This allows one to efficiently generate random networks with similar properties as an observed network, and the models can be used for several downstream tasks such as link prediction. Our methods are scalable to sparse graphs consisting of millions of nodes. Empirical evaluation demonstrates competitiveness in terms of both speed and accuracy with state-of-the-art methods—which are typically based on embedding the graph into some lowdimensional space— for link prediction, showcasing the potential of a more direct and interpretable probablistic model for this task.
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Anirudh Goyal
Shagun Sodhani
Jonathan Binas
Xue Bin Peng
Sergey Levine
Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavi… (see more)or. Often, this is addressed in the context of hierarchical reinforcement learning, where the aim is to decompose a policy into lower-level primitives or options, and a higher-level meta-policy that triggers the appropriate behaviors for a given situation. However, the meta-policy must still produce appropriate decisions in all states. In this work, we propose a policy design that decomposes into primitives, similarly to hierarchical reinforcement learning, but without a high-level meta-policy. Instead, each primitive can decide for themselves whether they wish to act in the current state. We use an information-theoretic mechanism for enabling this decentralized decision: each primitive chooses how much information it needs about the current state to make a decision and the primitive that requests the most information about the current state acts in the world. The primitives are regularized to use as little information as possible, which leads to natural competition and specialization. We experimentally demonstrate that this policy architecture improves over both flat and hierarchical policies in terms of generalization.
Small-GAN: Speeding Up GAN Training Using Core-sets
Samarth Sinha
Han Zhang
Anirudh Goyal
Augustus Odena
Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch siz… (see more)es. Unfortunately, using large batches is slow and expensive on conventional hardware. Thus, it would be nice if we could generate batches that were effectively large though actually small. In this work, we propose a method to do this, inspired by the use of Coreset-selection in active learning. When training a GAN, we draw a large batch of samples from the prior and then compress that batch using Coreset-selection. To create effectively large batches of 'real' images, we create a cached dataset of Inception activations of each training image, randomly project them down to a smaller dimension, and then use Coreset-selection on those projected activations at training time. We conduct experiments showing that this technique substantially reduces training time and memory usage for modern GAN variants, that it reduces the fraction of dropped modes in a synthetic dataset, and that it allows GANs to reach a new state of the art in anomaly detection.
Systematicity in a Recurrent Neural Network by Factorizing Syntax and Semantics
Jacob Russin
Jason Jo
R. O’Reilly
Standard methods in deep learning fail to capture compositional or systematic structure in their training data, as shown by their inability … (see more)to generalize outside of the training distribution. However, human learners readily generalize in this way, e.g. by applying known grammatical rules to novel words. The inductive biases that might underlie this powerful cognitive capacity remain unclear. Inspired by work in cognitive science suggesting a functional distinction between systems for syntactic and semantic processing, we implement a modification to an existing deep learning architecture, imposing an analogous separation. The resulting architecture substantially out-performs standard recurrent networks on the SCAN dataset, a compositional generalization task, without any additional supervision. Our work suggests that separating syntactic from semantic learning may be a useful heuristic for capturing compositional structure, and highlights the potential of using cognitive principles to inform inductive biases in deep learning.
On the interplay between noise and curvature and its effect on optimization and generalization
Valentin Thomas
Fabian Pedregosa
Bart van Merriënboer
Pierre-Antoine Manzagol
The speed at which one can minimize an expected loss using stochastic methods depends on two properties: the curvature of the loss and the v… (see more)ariance of the gradients. While most previous works focus on one or the other of these properties, we explore how their interaction affects optimization speed. Further, as the ultimate goal is good generalization performance, we clarify how both curvature and noise are relevant to properly estimate the generalization gap. Realizing that the limitations of some existing works stems from a confusion between these matrices, we also clarify the distinction between the Fisher matrix, the Hessian, and the covariance matrix of the gradients.
The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
Anirudh Goyal
Matthew Botvinick
Sergey Levine
In many applications, it is desirable to extract only the relevant information from complex input data, which involves making a decision abo… (see more)ut which input features are relevant. The information bottleneck method formalizes this as an information-theoretic optimization problem by maintaining an optimal tradeoff between compression (throwing away irrelevant input information), and predicting the target. In many problem settings, including the reinforcement learning problems we consider in this work, we might prefer to compress only part of the input. This is typically the case when we have a standard conditioning input, such as a state observation, and a ``privileged'' input, which might correspond to the goal of a task, the output of a costly planning algorithm, or communication with another agent. In such cases, we might prefer to compress the privileged input, either to achieve better generalization (e.g., with respect to goals) or to minimize access to costly information (e.g., in the case of communication). Practical implementations of the information bottleneck based on variational inference require access to the privileged input in order to compute the bottleneck variable, so although they perform compression, this compression operation itself needs unrestricted, lossless access. In this work, we propose the variational bandwidth bottleneck, which decides for each example on the estimated value of the privileged information before seeing it, i.e., only based on the standard input, and then accordingly chooses stochastically, whether to access the privileged input or not. We formulate a tractable approximation to this framework and demonstrate in a series of reinforcement learning experiments that it can improve generalization and reduce access to computationally costly information.