Portrait de Yoshua Bengio

Yoshua Bengio

Membre académique principal
Chaire en IA Canada-CIFAR
Professeur titulaire, Université de Montréal, Département d'informatique et de recherche opérationnelle
Directeur scientifique, Équipe de direction
Observateur, Conseil d'administration, Mila

Biographie

*Pour toute demande média, veuillez écrire à medias@mila.quebec.

Pour plus d’information, contactez Julie Mongeau, adjointe de direction à julie.mongeau@mila.quebec.

Reconnu comme une sommité mondiale en intelligence artificielle, Yoshua Bengio s’est surtout distingué par son rôle de pionnier en apprentissage profond, ce qui lui a valu le prix A. M. Turing 2018, le « prix Nobel de l’informatique », avec Geoffrey Hinton et Yann LeCun. Il est professeur titulaire à l’Université de Montréal, fondateur et directeur scientifique de Mila – Institut québécois d’intelligence artificielle, et codirige en tant que senior fellow le programme Apprentissage automatique, apprentissage biologique de l'Institut canadien de recherches avancées (CIFAR). Il occupe également la fonction de directeur scientifique d’IVADO.

En 2018, il a été l’informaticien qui a recueilli le plus grand nombre de nouvelles citations au monde. En 2019, il s’est vu décerner le prestigieux prix Killam. Depuis 2022, il détient le plus grand facteur d’impact (h-index) en informatique à l’échelle mondiale. Il est fellow de la Royal Society de Londres et de la Société royale du Canada, et officier de l’Ordre du Canada.

Soucieux des répercussions sociales de l’IA et de l’objectif que l’IA bénéficie à tous, il a contribué activement à la Déclaration de Montréal pour un développement responsable de l’intelligence artificielle.

Étudiants actuels

Stagiaire de recherche - Université du Québec à Rimouski
Maîtrise professionnelle - UdeM
Visiteur de recherche indépendant
Co-superviseur⋅e :
Visiteur de recherche indépendant - UQAR
Stagiaire de recherche - UQAR
Visiteur de recherche indépendant - MIT
Postdoctorat - UdeM
Co-superviseur⋅e :
Maîtrise professionnelle - UdeM
Collaborateur·rice de recherche - Université Paris-Saclay
Superviseur⋅e principal⋅e :
Doctorat - Massachusetts Institute of Technology
Doctorat - Barcelona University
Maîtrise professionnelle - UdeM
Stagiaire de recherche - UdeM
Maîtrise professionnelle - UdeM
Collaborateur·rice de recherche - UdeM
Collaborateur·rice de recherche
Visiteur de recherche indépendant - Technical University Munich (TUM)
Collaborateur·rice de recherche - UdeM
Collaborateur·rice alumni
Maîtrise professionnelle - UdeM
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Stagiaire de recherche - Imperial College London
Stagiaire de recherche - UdeM
Collaborateur·rice de recherche - UdeM
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Maîtrise professionnelle - UdeM
Visiteur de recherche indépendant - UdeM
Visiteur de recherche indépendant - Hong Kong University of Science and Technology (HKUST)
Collaborateur·rice de recherche - Ying Wu Coll of Computing
Maîtrise professionnelle - UdeM
Doctorat - Max-Planck-Institute for Intelligent Systems
Maîtrise professionnelle - UdeM
Visiteur de recherche indépendant - UdeM
Visiteur de recherche indépendant - UdeM
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Collaborateur·rice de recherche
Superviseur⋅e principal⋅e :
Maîtrise recherche - UdeM
Maîtrise professionnelle - UdeM
Visiteur de recherche indépendant - Technical University of Munich
Doctorat - École Polytechnique Fédérale de Lausanne
Collaborateur·rice de recherche
Superviseur⋅e principal⋅e :
Collaborateur·rice de recherche - Valence
Superviseur⋅e principal⋅e :
Collaborateur·rice de recherche - RWTH Aachen University (Rheinisch-Westfälische Technische Hochschule Aachen)
Superviseur⋅e principal⋅e :
Maîtrise professionnelle - UdeM
Collaborateur·rice alumni - UdeM
Doctorat - McGill
Superviseur⋅e principal⋅e :
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Doctorat - McGill
Superviseur⋅e principal⋅e :

Publications

Local Search GFlowNets
Minsu Kim
Taeyoung Yun
Emmanuel Bengio
Dinghuai Zhang
Sungsoo Ahn
Jinkyoo Park
Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their re… (voir plus)wards. GFlowNets exhibit a remarkable ability to generate diverse samples, yet occasionally struggle to consistently produce samples with high rewards due to over-exploration on wide sample space. This paper proposes to train GFlowNets with local search, which focuses on exploiting high-rewarded sample space to resolve this issue. Our main idea is to explore the local neighborhood via backtracking and reconstruction guided by backward and forward policies, respectively. This allows biasing the samples toward high-reward solutions, which is not possible for a typical GFlowNet solution generation scheme, which uses the forward policy to generate the solution from scratch. Extensive experiments demonstrate a remarkable performance improvement in several biochemical tasks. Source code is available: https://github.com/dbsxodud-11/ls_gfn.
Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks
Luca Scimeca
Alexander Rubinstein
Armand Nicolicioiu
Damien Teney
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to shortcut learning phenomena, where… (voir plus) a model may rely on erroneous, easy-to-learn, cues while ignoring reliable ones. In this work, we propose an ensemble diversification framework exploiting the generation of synthetic counterfactuals using Diffusion Probabilistic Models (DPMs). We discover that DPMs have the inherent capability to represent multiple visual cues independently, even when they are largely correlated in the training data. We leverage this characteristic to encourage model diversity and empirically show the efficacy of the approach with respect to several diversification objectives. We show that diffusion-guided diversification can lead models to avert attention from shortcut cues, achieving ensemble diversity performance comparable to previous methods requiring additional data collection.
AI and Catastrophic Risk
Tree Cross Attention
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Mohamed Osama Ahmed
RECOVER identifies synergistic drug combinations in vitro through sequential model optimization
Paul Bertin
Jarrid Rector-Brooks
Deepak Sharma
Thomas Gaudelet
Andrew Anighoro
Torsten Gross
Francisco Martínez-Peña
Eileen L. Tang
M.S. Suraj
Cristian Regep
Jeremy B.R. Hayter
Maksym Korablyov
Nicholas Valiante
Almer van der Sloot
Mike Tyers
Charles E.S. Roberts
Michael M. Bronstein
Luke L. Lairson
Jake P. Taylor-King
GEO-Bench: Toward Foundation Models for Earth Monitoring
Alexandre Lacoste
Nils Lehmann
Pau Rodriguez
Evan David Sherwin
Hannah Kerner
Björn Lütjens
Jeremy Andrew Irvin
David Dao
Hamed Alemohammad
Mehmet Gunturkun
Gabriel Huang
David Vazquez
Dava Newman
Stefano Ermon
Xiao Xiang Zhu
Recent progress in self-supervision has shown that pre-training large neural networks on vast amounts of unsupervised data can lead to subst… (voir plus)antial increases in generalization to downstream tasks. Such models, recently coined foundation models, have been transformational to the field of natural language processing. Variants have also been proposed for image data, but their applicability to remote sensing tasks is limited. To stimulate the development of foundation models for Earth monitoring, we propose a benchmark comprised of six classification and six segmentation tasks, which were carefully curated and adapted to be both relevant to the field and well-suited for model evaluation. We accompany this benchmark with a robust methodology for evaluating models and reporting aggregated results to enable a reliable assessment of progress. Finally, we report results for 20 baselines to gain information about the performance of existing models. We believe that this benchmark will be a driver of progress across a variety of Earth monitoring tasks.
SatBird: a Dataset for Bird Species Distribution Modeling using Remote Sensing and Citizen Science Data
Mélisande Teng
Amna Elmustafa
Benjamin Akera
Hager Radi
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
Chen Sun
Wannan Yang
Thomas Jiralerspong
Dane Malenfant
Benjamin Alsbury-Nealy
In real life, success is often contingent upon multiple critical steps that are distant in time from each other and from the final reward. T… (voir plus)hese critical steps are challenging to identify with traditional reinforcement learning (RL) methods that rely on the Bellman equation for credit assignment. Here, we present a new RL algorithm that uses offline contrastive learning to hone in on these critical steps. This algorithm, which we call Contrastive Retrospection (ConSpec), can be added to any existing RL algorithm. ConSpec learns a set of prototypes for the critical steps in a task by a novel contrastive loss and delivers an intrinsic reward when the current state matches one of the prototypes. The prototypes in ConSpec provide two key benefits for credit assignment: (i) They enable rapid identification of all the critical steps. (ii) They do so in a readily interpretable manner, enabling out-of-distribution generalization when sensory features are altered. Distinct from other contemporary RL approaches to credit assignment, ConSpec takes advantage of the fact that it is easier to retrospectively identify the small set of steps that success is contingent upon (and ignoring other states) than it is to prospectively predict reward at every taken step. ConSpec greatly improves learning in a diverse set of RL tasks. The code is available at the link: https://github.com/sunchipsster1/ConSpec
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
Lazar Atanackovic
Alexander Tong
Jason Hartford
Leo J Lee
Bo Wang
Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context
Oussama Boussif
Ghait Boukachab
Dan Assouline
Stefano Massaroli
Tianle Yuan
Loubna Benabbou
Solar power harbors immense potential in mitigating climate change by substantially reducing CO…
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network
Tristan Deleu
Mizu Nishikawa-Toomey
Jithendaraa Subramanian
Nikolay Malkin
Generative Flow Networks (GFlowNets), a class of generative models over discrete and structured sample spaces, have been previously applied … (voir plus)to the problem of inferring the marginal posterior distribution over the directed acyclic graph (DAG) of a Bayesian Network, given a dataset of observations. Based on recent advances extending this framework to non-discrete sample spaces, we propose in this paper to approximate the joint posterior over not only the structure of a Bayesian Network, but also the parameters of its conditional probability distributions. We use a single GFlowNet whose sampling policy follows a two-phase process: the DAG is first generated sequentially one edge at a time, and then the corresponding parameters are picked once the full structure is known. Since the parameters are included in the posterior distribution, this leaves more flexibility for the local probability models of the Bayesian Network, making our approach applicable even to non-linear models parametrized by neural networks. We show that our method, called JSP-GFN, offers an accurate approximation of the joint posterior, while comparing favorably against existing methods on both simulated and real data.
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
Stefano Massaroli
Michael Poli
Daniel Y Fu
Hermann Kumbong
Rom Nishijima Parnichkun
Aman Timalsina
David W. Romero
Quinn McIntyre
Beidi Chen
Atri Rudra
Ce Zhang
Christopher Re
Stefano Ermon
Recent advances in attention-free sequence models rely on convolutions as alternatives to the attention operator at the core of Transformers… (voir plus). In particular, long convolution sequence models have achieved state-of-the-art performance in many domains, but incur a significant cost during auto-regressive inference workloads -- naively requiring a full pass (or caching of activations) over the input sequence for each generated token -- similarly to attention-based models. In this paper, we seek to enable