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
Website
Google Scholar
LinkedIn
X

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

Jamal Abou Haibeh
Collaborating Alumni - McGill University
Github
Google Scholar
Mohammed Abukalam
Collaborating Alumni - Université de Montréal
Github
Berkes Anaïs
Collaborating researcher - Cambridge University
Principal supervisor :
David Rolnick
Website
Github
Google Scholar
Rim Assouel
PhD - Université de Montréal
Junyeob BAEK
Independent visiting researcher - KAIST
Website
Github
Google Scholar
Stefan Bauer
Independent visiting researcher
Co-supervisor :
Guillaume Lajoie
Google Scholar
Paul Bertin
PhD - Université de Montréal
Shahana Chatterjee
Collaborating researcher - N/A
Principal supervisor :
David Rolnick
Google Scholar
Xiaoyin Chen
PhD - Université de Montréal
Sanghyeok Choi
Collaborating researcher - KAIST
Website
Github
Google Scholar
Tristan Deleu
PhD - Université de Montréal
Website
Github
Google Scholar
Aniket Didolkar
PhD - Université de Montréal
Website
Github
Google Scholar
Abdessamad EL KABID
Research Intern - Université de Montréal
Co-supervisor :
Loubna Benabbou
Github
Eric Elmoznino
PhD - Université de Montréal
Co-supervisor :
Guillaume Lajoie
Website
Github
Google Scholar
Léna Ezzine
PhD - Université de Montréal
Github
Jean-Pierre Falet
PhD - Université de Montréal
Co-supervisor :
Guillaume Lajoie
Website
Github
Google Scholar
Leo Feng
PhD - Université de Montréal
leo.feng@mila.quebec
Website
Google Scholar
Ivan Grega
Research Intern - Université de Montréal
Github
Pietro Greiner
PhD
Google Scholar
Mohsin Hasan
PhD - Université de Montréal
mohsin.hasan@mila.quebec
Website
Github
Google Scholar
Edward Hu
PhD - Université de Montréal
Moksh Jain
PhD - Université de Montréal
moksh.jain@mila.quebec
Website
Github
Google Scholar
Thomas Jiralerspong
PhD - Université de Montréal
Principal supervisor :
Guillaume Lajoie
Website
Github
Google Scholar
Younesse Kaddar
Collaborating Alumni - Université de Montréal
Website
Github
Hyeonah Kim
Postdoctorate - Université de Montréal
Principal supervisor :
Alex Hernandez
Yaroslav KIVVA
Collaborating researcher - Université de Montréal
Github
Google Scholar
Salem Lahlou
Collaborating Alumni - Université de Montréal
Github
Tabitha Edith Lee
Postdoctorate - Université de Montréal
Principal supervisor :
Glen Berseth
Website
Github
Google Scholar
Seanie Lee
Collaborating Alumni - Université de Montréal
Website
Github
Google Scholar
Chenghao Liu
Collaborating Alumni
Website
Github
Google Scholar
Zhen Liu
Collaborating Alumni - Université de Montréal
Principal supervisor :
Liam Paull
Kanika Madan
PhD - Université de Montréal
Nikolay Malkin
Collaborating Alumni - Université de Montréal
Website
Github
Google Scholar
Cristian Dragos Manta
PhD - Université de Montréal
Co-supervisor :
Dhanya Sridhar
Github
Sören Mindermann
Collaborating researcher - Université de Montréal
Website
Google Scholar
Sarthak Mittal
PhD - Université de Montréal
Principal supervisor :
Guillaume Lajoie
Website
Github
Google Scholar
Jama Mohamud
PhD - Université de Montréal
Principal supervisor :
Mirco Ravanelli
Website
Github
Google Scholar
Cyrus Neary
Postdoctorate - Université de Montréal
Principal supervisor :
Glen Berseth
Website
Github
Google Scholar
Phong Nguyen
Independent visiting researcher - Université de Montréal
Padideh Nouri
PhD - Université de Montréal
Principal supervisor :
Doina Precup
Website
Github
Google Scholar
Ali Parviz
Collaborating researcher - Ying Wu Coll of Computing
Google Scholar
Lena Podina
PhD - University of Waterloo
Principal supervisor :
David Rolnick
Github
Google Scholar
Nassim Rahaman
Collaborating Alumni - Max-Planck-Institute for Intelligent Systems
Amine RAZIG
Research Intern - Université de Montréal
Co-supervisor :
Loubna Benabbou
Website
Jarrid Rector-Brooks
PhD - Université de Montréal
Danyal REHMAN
Postdoctorate - Université de Montréal
Github
James Requeima
Independent visiting researcher - Université de Montréal
Oli RICHARDSON
Postdoctorate - Université de Montréal
Website
Github
Google Scholar
Camille Rochefort-Boulanger
PhD - Université de Montréal
Principal supervisor :
Julie Hussin
Github
Victor Schmidt
Collaborating Alumni - Université de Montréal
Website
Github
Google Scholar
Luca Scimeca
Postdoctorate - Université de Montréal
Website
Github
Google Scholar
Dragos Secrieru
Master's Research - Université de Montréal
Marcin Sendera
Collaborating Alumni - Université de Montréal
Github
Google Scholar
Vedant Shah
Master's Research - Université de Montréal
Website
Github
Google Scholar
Divya Sharma
Postdoctorate
Website
Github
Marco Stock
Independent visiting researcher - Technical University of Munich
marco.stock@tum.de
Github
Mélisande Astrid Crystal Teng
PhD - Université de Montréal
Co-supervisor :
Hugo Larochelle
Website
Github
Alex Tong
Postdoctorate - Université de Montréal
alexander.tong@mila.quebec
Website
Github
Google Scholar
Donna Vakalis
Postdoctorate - Université de Montréal
Co-supervisor :
David Rolnick
Website
Github
Google Scholar
Siddarth Venkatraman
PhD - Université de Montréal
Principal supervisor :
Glen Berseth
Website
Github
Google Scholar
Leah WAIRIMU
Collaborating researcher - Université de Montréal
Github
Omar G. Younis
Collaborating researcher
Website
Github
Google Scholar
Taeyoung YUN
Research Intern - Université de Montréal
Github
Tianyu Zhang
PhD - Université de Montréal
Website
Github
Google Scholar
Nicole Zhang
PhD - McGill University
Principal supervisor :
Mathieu Blanchette
Github
Google Scholar
Dinghuai Zhang
PhD - Université de Montréal
Principal supervisor :
Aaron Courville
Website
Github
Harry Zhao
PhD - McGill University
Principal supervisor :
Doina Precup
Website
Github
Google Scholar

Publications

GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, w… (see more)ith a training objective that makes them approximately sample in proportion to a given reward function. In this paper, we show a number of additional theoretical properties of GFlowNets. They can be used to estimate joint probability distributions and the corresponding marginal distributions where some variables are unspecified and, of particular interest, can represent distributions over composite objects like sets and graphs. GFlowNets amortize the work typically done by computationally expensive MCMC methods in a single but trained generative pass. They could also be used to estimate partition functions and free energies, conditional probabilities of supersets (supergraphs) given a subset (subgraph), as well as marginal distributions over all supersets (supergraphs) of a given set (graph). We introduce variations enabling the estimation of entropy and mutual information, sampling from a Pareto frontier, connections to reward-maximizing policies, and extensions to stochastic environments, continuous actions and modular energy functions.
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, w… (see more)ith a training objective that makes them approximately sample in proportion to a given reward function. In this paper, we show a number of additional theoretical properties of GFlowNets. They can be used to estimate joint probability distributions and the corresponding marginal distributions where some variables are unspecified and, of particular interest, can represent distributions over composite objects like sets and graphs. GFlowNets amortize the work typically done by computationally expensive MCMC methods in a single but trained generative pass. They could also be used to estimate partition functions and free energies, conditional probabilities of supersets (supergraphs) given a subset (subgraph), as well as marginal distributions over all supersets (supergraphs) of a given set (graph). We introduce variations enabling the estimation of entropy and mutual information, sampling from a Pareto frontier, connections to reward-maximizing policies, and extensions to stochastic environments, continuous actions and modular energy functions.
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, w… (see more)ith a training objective that makes them approximately sample in proportion to a given reward function. In this paper, we show a number of additional theoretical properties of GFlowNets. They can be used to estimate joint probability distributions and the corresponding marginal distributions where some variables are unspecified and, of particular interest, can represent distributions over composite objects like sets and graphs. GFlowNets amortize the work typically done by computationally expensive MCMC methods in a single but trained generative pass. They could also be used to estimate partition functions and free energies, conditional probabilities of supersets (supergraphs) given a subset (subgraph), as well as marginal distributions over all supersets (supergraphs) of a given set (graph). We introduce variations enabling the estimation of entropy and mutual information, sampling from a Pareto frontier, connections to reward-maximizing policies, and extensions to stochastic environments, continuous actions and modular energy functions.
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
GFlowNet Foundations
Yoshua Bengio
Tristan Deleu
Edward J Hu
Salem Lahlou
Mo Tiwari
Emmanuel Bengio
Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, w… (see more)ith a training objective that makes them approximately sample in proportion to a given reward function. In this paper, we show a number of additional theoretical properties of GFlowNets. They can be used to estimate joint probability distributions and the corresponding marginal distributions where some variables are unspecified and, of particular interest, can represent distributions over composite objects like sets and graphs. GFlowNets amortize the work typically done by computationally expensive MCMC methods in a single but trained generative pass. They could also be used to estimate partition functions and free energies, conditional probabilities of supersets (supergraphs) given a subset (subgraph), as well as marginal distributions over all supersets (supergraphs) of a given set (graph). We introduce variations enabling the estimation of entropy and mutual information, sampling from a Pareto frontier, connections to reward-maximizing policies, and extensions to stochastic environments, continuous actions and modular energy functions.
2021-11-17
ArXiv (preprint)
arxiv.org
arxiv.org
Discrete-Valued Neural Communication
Dianbo Liu
Alex Lamb
Kenji Kawaguchi
Anirudh Goyal
Chen Sun
Michael Curtis Mozer
Yoshua Bengio
Deep learning has advanced from fully connected architectures to structured models organized into components, e.g., the transformer composed… (see more) of positional elements, modular architectures divided into slots, and graph neural nets made up of nodes. In structured models, an interesting question is how to conduct dynamic and possibly sparse communication among the separate components. Here, we explore the hypothesis that restricting the transmitted information among components to discrete representations is a beneficial bottleneck. The motivating intuition is human language in which communication occurs through discrete symbols. Even though individuals have different understandings of what a"cat"is based on their specific experiences, the shared discrete token makes it possible for communication among individuals to be unimpeded by individual differences in internal representation. To discretize the values of concepts dynamically communicated among specialist components, we extend the quantization mechanism from the Vector-Quantized Variational Autoencoder to multi-headed discretization with shared codebooks and use it for discrete-valued neural communication (DVNC). Our experiments show that DVNC substantially improves systematic generalization in a variety of architectures -- transformers, modular architectures, and graph neural networks. We also show that the DVNC is robust to the choice of hyperparameters, making the method very useful in practice. Moreover, we establish a theoretical justification of our discretization process, proving that it has the ability to increase noise robustness and reduce the underlying dimensionality of the model.
openreview.net
Gradient Starvation: A Learning Proclivity in Neural Networks
Mohammad Pezeshki
Sékou-Oumar Kaba
Yoshua Bengio
Aaron Courville
Doina Precup
Guillaume Lajoie
We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks… (see more). Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task, despite the presence of other predictive features that fail to be discovered. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks. Using tools from Dynamical Systems theory, we identify simple properties of learning dynamics during gradient descent that lead to this imbalance, and prove that such a situation can be expected given certain statistical structure in training data. Based on our proposed formalism, we develop guarantees for a novel regularization method aimed at decoupling feature learning dynamics, improving accuracy and robustness in cases hindered by gradient starvation. We illustrate our findings with simple and real-world out-of-distribution (OOD) generalization experiments.
openreview.net