Laurent Charlin

Biography

Laurent Charlin is a Canada CIFAR AI Chair and core academic member of Mila – Quebec Artificial Intelligence Institute, as well as an associate professor at HEC Montréal, the business school affiliated with Université de Montréal.

Charlin’s research focuses on developing novel machine learning models to aid in decision-making. Recent work has focused on learning from data that changes over time, and on applications in fields such as recommender systems and optimization.

He has a number of highly cited publications on dialogue systems (chatbots). He co-developed the Toronto Paper Matching System (TPMS), which has been widely used by computer science conferences for matching reviewers to papers. He has also given MOOCs, introductory talks and media interviews to contribute to knowledge transfer and improve AI literacy.

Current Students

Shubham Agarwal

Postdoctorate - HEC Montréal

Co-supervisor :

Dieng Awa

Master's Research - HEC Montréal

David Berger

PhD - Université de Montréal

Anirudh Buvanesh

PhD - Université de Montréal

Co-supervisor :

Aaron Courville

anirudb1102@gmail.com

Github

Sal Elkafrawy

PhD - Université de Montréal

Postdoctorate

PhD - Université Laval

Principal supervisor :

Cem Subakan

Ben Hudson

PhD - Université de Montréal

Co-supervisor :

Emma Frejinger

ben.hudson@mila.quebec

Website

Github

Mizu Nishikawa-Toomey

PhD - Université de Montréal

Co-supervisor :

PhD - Concordia University

Principal supervisor :

PhD - Université de Montréal

Emiliano Penaloza

PhD - Université de Montréal

Website

Github

Omar Salemohamed

PhD - Université de Montréal

Yipeng Zhang

PhD - Université de Montréal

Publications

Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network

Tristan Deleu

Mizu Nishikawa-Toomey

Jithendaraa Subramanian

Nikolay Malkin

Yoshua Bengio

Generative Flow Networks (GFlowNets), a class of generative models over discrete and structured sample spaces, have been previously applied … (see more)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.

Should We Feed the Trolls? Using Marketer-Generated Content to Explain Average Toxicity and Product Usage

Marcelo Vinhal Nepomuceno

Hooman Rahemi

Tolga Cenesizoglu

2023-06-29

Journal of Interactive Marketing (published)

Towards Compute-Optimal Transfer Learning

Massimo Caccia

Alexandre Galashov

Arthur Douillard

Amal Rannen-Triki

Dushyant Rao

Michela Paganini

Marc'aurelio Ranzato

Razvan Pascanu

2023-04-25

ArXiv (preprint)

From IID to the Independent Mechanisms assumption in continual learning

Oleksiy Ostapenko

Pau Rodriguez

Alexandre Lacoste

Current machine learning algorithms are successful in learning clearly defined tasks from large i.i.d. data. Continual learning (CL) require… (see more)s learning without iid-ness and developing algorithms capable of knowledge retention and transfer, the latter can be boosted through systematic generalization. Dropping the i.i.d. assumption requires replacing it with another hypothesis. While there are several candidates, here we advocate that the independent mechanism assumption (IM) (Sch¨olkopf et al., 2012) is a useful hypothesis for representing knowledge in a form, that makes it easy to adapt to new tasks in CL. Specifically, we review several types of distribution shifts that are common in CL and point out in which way a system that represents knowledge in the form of causal modules may outperform monolithic counterparts in CL. Intuitively, the efficacy of IM solution emerges since (i) causal modules learn mechanisms invariant across domains; (ii) if causal mechanisms must be updated, modularity can enable efficient and sparse updates.

2023-01-11

AAAI.org/2023/Bridge/CCBridge (published)

From IID to the Independent Mechanisms assumption in continual learning

Oleksiy Ostapenko

Pau Rodriguez

Alexandre Lacoste

2023-01-11

AAAI.org/2023/Bridge/CCBridge (accepted)

proceedings.mlr.press

Iorl: Inductive-Offline-Reinforcement-Learning for Traffic Signal Control Warmstarting

FranÃ§ois-Xavier Devailly

Denis Larocque

2023-01-01

Social Science Research Network (published)

Price Forecasting in the Ontario Electricity Market via TriConvGRU Hybrid Model: Univariate vs. Multivariate Frameworks

Behdad Ehsani

Pierre-Olivier Pineau

2023-01-01

SSRN Electronic Journal (published)

Continual Learning with Foundation Models: An Empirical Study of Latent Replay

Oleksiy Ostapenko

Timothee LESORT

Pau Rodriguez

Md Rifat Arefin

Arthur Douillard

Irina Rish

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of… (see more) downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models as a foundation for downstream continual learning (CL) scenarios. Our goal is twofold. First, we want to understand the compute-accuracy trade-off between CL in the raw-data space and in the latent space of pre-trained encoders. Second, we investigate how the characteristics of the encoder, the pre-training algorithm and data, as well as of the resulting latent space affect CL performance. For this, we compare the efficacy of various pre-trained models in large-scale benchmarking scenarios with a vanilla replay setting applied in the latent and in the raw-data space. Notably, this study shows how transfer, forgetting, task similarity and learning are dependent on the input data characteristics and not necessarily on the CL algorithms. First, we show that under some circumstances reasonable CL performance can readily be achieved with a non-parametric classifier at negligible compute. We then show how models pre-trained on broader data result in better performance for various replay sizes. We explain this with representational similarity and transfer properties of these representations. Finally, we show the effectiveness of self-supervised pre-training for downstream domains that are out-of-distribution as compared to the pre-training domain. We point out and validate several research directions that can further increase the efficacy of latent CL including representation ensembling. The diverse set of datasets used in this study can serve as a compute-efficient playground for further CL research. We will publish the code.

2022-11-28

Proceedings of The 1st Conference on Lifelong Learning Agents (published)

proceedings.mlr.press

Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayes

Mizu Nishikawa-Toomey

Tristan Deleu

Jithendaraa Subramanian

Yoshua Bengio

Bayesian causal structure learning aims to learn a posterior distribution over directed acyclic graphs (DAGs), and the mechanisms that defin… (see more)e the relationship between parent and child variables. By taking a Bayesian approach, it is possible to reason about the uncertainty of the causal model. The notion of modelling the uncertainty over models is particularly crucial for causal structure learning since the model could be unidentifiable when given only a finite amount of observational data. In this paper, we introduce a novel method to jointly learn the structure and mechanisms of the causal model using Variational Bayes, which we call Variational Bayes-DAG-GFlowNet (VBG). We extend the method of Bayesian causal structure learning using GFlowNets to learn not only the posterior distribution over the structure, but also the parameters of a linear-Gaussian model. Our results on simulated data suggest that VBG is competitive against several baselines in modelling the posterior over DAGs and mechanisms, while offering several advantages over existing methods, including the guarantee to sample acyclic graphs, and the flexibility to generalize to non-linear causal mechanisms.

2022-11-04

ArXiv (preprint)

Attention for Compositional Modularity

Oleksiy Ostapenko

Pau Rodriguez

Alexandre Lacoste

Modularity and compositionality are promising inductive biases for addressing longstanding problems in machine learning such as better syste… (see more)matic generalization, as well as better transfer and lower forgetting in the context of continual learning. Here we study how attention-based module selection can help achieve composi-tonal modularity – i.e. decomposition of tasks into meaningful sub-tasks which are tackled by independent architectural entities that we call modules. These sub-tasks must be reusable and the system should be able to learn them without additional supervision. We design a simple experimental setup in which the model is trained to solve mathematical equations with multiple math operations applied sequentially. We study different attention-based module selection strategies, inspired by the principles introduced in the recent literature. We evaluate the method’s ability to learn modules that can recover the underling sub-tasks (operation) used for data generation, as well as the ability to generalize compositionally. We find that meaningful module selection (i.e. routing) is the key to compositional generalization. Further, without access to the privileged information about which part of the input should be used for module selection, the routing component performs poorly for samples that are compositionally out of training distribution. We find that the the main reason for this lies in the routing component, since many of the tested methods perform well OOD if we report the performance of the best performing path at test time. Additionally, we study the role of the number of primitives, the number of training points and bottlenecks for modular specialization.

2022-10-20

NeurIPS.cc/2022/Workshop/Attention (poster)

Challenging Common Assumptions about Catastrophic Forgetting

Timothee LESORT

Oleksiy Ostapenko

Pau Rodriguez

Md Rifat Arefin

Diganta Misra

Irina Rish

Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research fiel… (see more)d. Unfortunately, training a model on new data usually compromises the performance on past data. In the CL literature, this effect is referred to as catastrophic forgetting (CF). CF has been largely studied, and a plethora of methods have been proposed to address it on short sequences of non-overlapping tasks. In such setups, CF always leads to a quick and significant drop in performance in past tasks. Nevertheless, despite CF, recent work showed that SGD training on linear models accumulates knowledge in a CL regression setup. This phenomenon becomes especially visible when tasks reoccur. We might then wonder if DNNs trained with SGD or any standard gradient-based optimization accumulate knowledge in such a way. Such phenomena would have interesting consequences for applying DNNs to real continual scenarios. Indeed, standard gradient-based optimization methods are significantly less computationally expensive than existing CL algorithms. In this paper, we study the progressive knowledge accumulation (KA) in DNNs trained with gradient-based algorithms in long sequences of tasks with data re-occurrence. We propose a new framework, SCoLe (Scaling Continual Learning), to investigate KA and discover that catastrophic forgetting has a limited effect on DNNs trained with SGD. When trained on long sequences with data sparsely re-occurring, the overall accuracy improves, which might be counter-intuitive given the CF phenomenon. We empirically investigate KA in DNNs under various data occurrence frequencies and propose simple and scalable strategies to increase knowledge accumulation in DNNs.

2022-07-10

ArXiv (preprint)

IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Control

FranÃ§ois-Xavier Devailly

Denis Larocque

Scaling adaptive traffic signal control involves dealing with combinatorial state and action spaces. Multi-agent reinforcement learning atte… (see more)mpts to address this challenge by distributing control to specialized agents. However, specialization hinders generalization and transferability, and the computational graphs underlying neural-network architectures—dominating in the multi-agent setting—do not offer the flexibility to handle an arbitrary number of entities which changes both between road networks, and over time as vehicles traverse the network. We introduce Inductive Graph Reinforcement Learning (IG-RL) based on graph-convolutional networks which adapts to the structure of any road network, to learn detailed representations of traffic signal controllers and their surroundings. Our decentralized approach enables learning of a transferable-adaptive-traffic-signal-control policy. After being trained on an arbitrary set of road networks, our model can generalize to new road networks and traffic distributions, with no additional training and a constant number of parameters, enabling greater scalability compared to prior methods. Furthermore, our approach can exploit the granularity of available data by capturing the (dynamic) demand at both the lane level and the vehicle level. The proposed method is tested on both road networks and traffic settings never experienced during training. We compare IG-RL to multi-agent reinforcement learning and domain-specific baselines. In both synthetic road networks and in a larger experiment involving the control of the 3,971 traffic signals of Manhattan, we show that different instantiations of IG-RL outperform baselines.

2022-07-01

IEEE Transactions on Intelligent Transportation Systems (published)