Portrait of Aaron Courville

Aaron Courville

Core Academic Member
courvila@mila.quebec
Canada CIFAR AI Chair
Associate Professor, Université de Montréal, Department of Computer Science and Operations Research

Biography

Aaron Courville is a professor in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal. He has a PhD from the Robotics Institute, Carnegie Mellon University.

Courville was an early contributor to deep learning: he is a founding member of Mila – Quebec Artificial Intelligence Institute, a fellow in CIFAR’s Learning in Machines & Brains program and, with Ian Goodfellow and Yoshua Bengio, co-wrote the seminal textbook on deep learning.

His current research focuses on the development of deep learning models and methods. He is particularly interested in reinforcement learning, deep generative models and multimodal ML, as well as their applications, such as computer vision and natural language processing.

Courville holds a Canada CIFAR AI Chair and a Canada Research Chair in Learning Representations that Generalize Systematically. His research has been supported by Microsoft Research, Samsung, Hitachi, Sony and Google (Focused Research Award).

Current Students

Adrien Ali Taiga
PhD - Université de Montréal
Co-supervisor :
Marc Gendron-Bellemare
adrien.taiga@mila.quebec
Alexandre Diz Ganito
Master's Research - Université de Montréal
alexandre.ganito@mila.quebec
Amr Khalifa
PhD - Université de Montréal
amr-khalifa.alshaykh@mila.quebec
Github
Andrei Nicolicioiu
PhD - Université de Montréal
andrei.nicolicioiu@mila.quebec
Website
Google Scholar
Ankit Vani
PhD - Université de Montréal
vanianki@mila.quebec
Website
Github
Google Scholar
Ching Lam Choi
Undergraduate - Université de Montréal
ching-lam.choi@mila.quebec
Website
Github
Google Scholar
Christos Tsirigotis
PhD - Université de Montréal
Principal supervisor :
(Rex) Devon Hjelm
tsirigoc@mila.quebec
Github
Google Scholar
Dinghuai Zhang
PhD - Université de Montréal
Co-supervisor :
Yoshua Bengio
dinghuai.zhang@mila.quebec
Website
Esra'a Saleh
PhD - Université de Montréal
Principal supervisor :
Glen Berseth
esraa.saleh@mila.quebec
Website
Google Scholar
Evgenii Nikishin
PhD - Université de Montréal
Principal supervisor :
Pierre-Luc Bacon
evgenii.nikishin@mila.quebec
Website
Github
Google Scholar
Faruk Ahmed
PhD - Université de Montréal
faruk.ahmed@mila.quebec
Github
Google Scholar
Johan Samir Obando Ceron
PhD - Université de Montréal
Co-supervisor :
Pablo Samuel Castro
johan.ceron@mila.quebec
Github
Google Scholar
Juan Duque
PhD - Université de Montréal
juan.duque@mila.quebec
Website
Google Scholar
Manoosh Samiei
PhD - Université de Montréal
manoosh.samiei@mila.quebec
Website
Github
Google Scholar
Max Schwarzer
PhD - Université de Montréal
Co-supervisor :
Marc Gendron-Bellemare
schwarzm@mila.quebec
Hattie Zhou
PhD - Université de Montréal
Principal supervisor :
Hugo Larochelle
mengfei.zhou@mila.quebec
Michael Noukhovitch
PhD - Université de Montréal
noukhovm@mila.quebec
Website
Github
Google Scholar
Morgane Moss
Collaborating researcher
morgane.moss@mila.quebec
Muqeeth Mohammed
Collaborating researcher - Université de Montréal
mohammed.muqeeth@mila.quebec
Website
Github
Google Scholar
Pietro Mazzaglia
Research Intern - Ghent University
pietro.mazzaglia@mila.quebec
Website
Github
Google Scholar
Razvan Ciuca
Research Intern - Université de Montréal
razvan.ciuca@mila.quebec
Github
Rishabh Agarwal
PhD - Université de Montréal
Co-supervisor :
Marc Gendron-Bellemare
agarwalr@mila.quebec
Website
Github
Google Scholar
Samuel Lavoie Marchildon
PhD - Université de Montréal
samuel.lavoie@mila.quebec
Sarvjeet Ghotra
Master's Research - Université de Montréal
Principal supervisor :
Aishwarya Agrawal
sarvjeet-singh.ghotra@mila.quebec
Github
Google Scholar
Arian Hosseini
PhD - Université de Montréal
hosseise@mila.quebec
Website
Github
Google Scholar
Shawn Tan
PhD - Université de Montréal
tanjings@mila.quebec
Website
Github
Google Scholar
Timotheus Cooijmans
PhD - Université de Montréal
cooijmat@mila.quebec
Website
Github
Google Scholar
Xiaofeng Zhang
PhD - Université de Montréal
xiaofeng.zhang@mila.quebec
Website
Yusong Wu
PhD - Université de Montréal
Principal supervisor :
Anna (Cheng-Zhi) Huang
wu.yusong@mila.quebec
Zhixuan Lin
PhD - Université de Montréal
zhixuan.lin@mila.quebec
Website
Github
Google Scholar

Publications

Invariant representation driven neural classifier for anti-QCD jet tagging
Taoli Cheng
Aaron Courville
2022-10-24
Journal of High Energy Physics (published)
doi.org
arxiv.org
VIM: Variational Independent Modules for Video Prediction
Rim Assouel
Lluis Castrejon
Aaron Courville
Nicolas Ballas
Yoshua Bengio
We introduce a variational inference model called VIM, for Variational Independent Modules, for sequential data that learns and infers laten… (see more)t representations as a set of objects and discovers modular causal mechanisms over these objects. These mechanisms - which we call modules - are independently parametrized, define the stochastic transitions of entities and are shared across entities. At each time step, our model infers from a low-level input sequence a high-level sequence of categorical latent variables to select which transition modules to apply to which high-level object. We evaluate this model in video prediction tasks where the goal is to predict multi-modal future events given previous observations. We demonstrate empirically that VIM can model 2D visual sequences in an interpretable way and is able to identify the underlying dynamically instantiated mechanisms of the generation process. We additionally show that the learnt modules can be composed at test time to generalize to out-of-distribution observations.
2022-06-28
Proceedings of the First Conference on Causal Learning and Reasoning (published)
proceedings.mlr.press
openreview.net
Multi-label Iterated Learning for Image Classification with Label Ambiguity
Sai Rajeswar
Pau Rodriguez
Soumye Singhal
David Vazquez
Aaron Courville
Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that da… (see more)tasets like ImageNet are weakly labeled since images with multiple object classes present are assigned a single label. This ambiguity biases models towards a single prediction, which could result in the suppression of classes that tend to co-occur in the data. Inspired by language emergence literature, we propose multi-label iterated learning (MILe) to incorporate the inductive biases of multi-label learning from single labels using the framework of iterated learning. MILe is a simple yet effective procedure that builds a multi-label description of the image by propagating binary predictions through successive generations of teacher and student networks with a learning bottleneck. Experiments show that our approach exhibits systematic benefits on ImageNet accuracy as well as ReaL F1 score, which indicates that MILe deals better with label ambiguity than the standard training procedure, even when fine-tuning from self-supervised weights. We also show that MILe is effective reducing label noise, achieving state-of-the-art performance on real-world large-scale noisy data such as WebVision. Furthermore, MILe improves performance in class incremental settings such as IIRC and it is robust to distribution shifts. Code: https://github.com/rajeswar18/MILe
2022-06-18
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)
doi.org
arxiv.org
Unsupervised Dependency Graph Network
Yikang Shen
Shawn Tan
Alessandro Sordoni
Peng Li
Jie Zhou
Aaron Courville
2022-05-01
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (published)
doi.org
Fortuitous Forgetting in Connectionist Networks
Hattie Zhou
Ankit Vani
Hugo Larochelle
Aaron Courville
Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact b… (see more)e favorable to learning. We introduce"forget-and-relearn"as a powerful paradigm for shaping the learning trajectories of artificial neural networks. In this process, the forgetting step selectively removes undesirable information from the model, and the relearning step reinforces features that are consistently useful under different conditions. The forget-and-relearn framework unifies many existing iterative training algorithms in the image classification and language emergence literature, and allows us to understand the success of these algorithms in terms of the disproportionate forgetting of undesirable information. We leverage this understanding to improve upon existing algorithms by designing more targeted forgetting operations. Insights from our analysis provide a coherent view on the dynamics of iterative training in neural networks and offer a clear path towards performance improvements.
2022-01-28
ICLR.cc/2022/Conference (poster)
openreview.net
openreview.net
Invariant representation driven neural classifier for anti-QCD jet tagging
Taoli Cheng
Aaron Courville
2022-01-18
ArXiv (preprint)
doi.org
arxiv.org
Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
Rishabh Agarwal
Max Schwarzer
Pablo Samuel Castro
Aaron Courville
Marc Gendron-Bellemare
openreview.net
Unsupervised Dependency Graph Network
Yikang Shen
Shawn Tan
Alessandro Sordoni
Peng Li
Jie Zhou
Aaron Courville
Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, s… (see more)ome self-attention heads correspond well to individual dependency types. Inspired by these developments, we propose a new competitive mechanism that encourages these attention heads to model different dependency relations. We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task. Experiment results show that UDGN achieves very strong unsupervised dependency parsing performance without gold POS tags and any other external information. The competitive gated heads show a strong correlation with human-annotated dependency types. Furthermore, the UDGN can also achieve competitive performance on masked language modeling and sentence textual similarity tasks.
2022-01-01
Annual Meeting of the Association for Computational Linguistics (published)
doi.org
Multi-label Iterated Learning for Image Classification with Label Ambiguity
Sai Rajeswar
Pau Rodriguez
Soumye Singhal
David Vazquez
Aaron Courville
Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that da… (see more)tasets like ImageNet are weakly labeled since images with multiple object classes present are assigned a single label. This ambiguity biases models towards a single prediction, which could result in the suppression of classes that tend to co-occur in the data. Inspired by language emergence literature, we propose multi-label iterated learning (MILe) to incorporate the inductive biases of multi-label learning from single labels using the framework of iterated learning. MILe is a simple yet effective procedure that builds a multi-label description of the image by propagating binary predictions through successive generations of teacher and student networks with a learning bottleneck. Experiments show that our approach exhibits systematic benefits on ImageNet accuracy as well as ReaL F1 score, which indicates that MILe deals better with label ambiguity than the standard training procedure, even when fine-tuning from self-supervised weights. We also show that MILe is effective reducing label noise, achieving state-of-the-art performance on real-world large-scale noisy data such as WebVision. Furthermore, MILe improves performance in class incremental settings such as IIRC and it is robust to distribution shifts. Code: https://github.com/rajeswar18/MILe
2021-11-23
ArXiv (preprint)
doi.org
arxiv.org
Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle
Yikang Shen
Shawn Tan
Alessandro Sordoni
Siva Reddy
Aaron Courville
Syntax is fundamental to our thinking about language. Failing to capture the structure of input language could lead to generalization proble… (see more)ms and over-parametrization. In the present work, we propose a new syntax-aware language model: Syntactic Ordered Memory (SOM). The model explicitly models the structure with an incremental parser and maintains the conditional probability setting of a standard language model (left-to-right). To train the incremental parser and avoid exposure bias, we also propose a novel dynamic oracle, so that SOM is more robust to wrong parsing decisions. Experiments show that SOM can achieve strong results in language modeling, incremental parsing, and syntactic generalization tests while using fewer parameters than other models.
2021-06-01
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (published)
doi.org
arxiv.org
Understanding by Understanding Not: Modeling Negation in Language Models
Arian Hosseini
Siva Reddy
Dzmitry Bahdanau
(Rex) Devon Hjelm
Alessandro Sordoni
Aaron Courville
Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language mode… (see more)ls often handle negation incorrectly. To improve language models in this regard, we propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences from a raw text corpus. By training BERT with the resulting combined objective we reduce the mean top 1 error rate to 4% on the negated LAMA dataset. We also see some improvements on the negated NLI benchmarks.
2021-06-01
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (published)
doi.org
arxiv.org
DATA-EFFICIENT REINFORCEMENT LEARNING
Nitarshan Rajkumar
Michael Noukhovitch
Ankesh Anand
Laurent Charlin
(Rex) Devon Hjelm
Philip Bachman
Aaron Courville
Data efficiency poses a major challenge for deep reinforcement learning. We approach this issue from the perspective of self-supervised repr… (see more)esentation learning, leveraging reward-free exploratory data to pretrain encoder networks. We employ a novel combination of latent dynamics modelling and goal-reaching objectives, which exploit the inherent structure of data in reinforcement learning. We demonstrate that our method scales well with network capacity and pretraining data. When evaluated on the Atari 100k data-efficiency benchmark, our approach significantly outperforms previous methods combining unsupervised pretraining with task-specific finetuning, and approaches human-level performance.
2021-01-01
(published)
www.semanticscholar.org