Guillaume Rabusseau

Biography

I have been an assistant professor at Mila – Quebec Artificial Intelligence Institute and in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal (UdeM) since September 2018. I was awarded a Canada CIFAR AI Chair in March 2019. Before joining UdeM, I was a postdoctoral research fellow in the Reasoning and Learning Lab at McGill University, where I worked with Prakash Panangaden, Joelle Pineau and Doina Precup.

I obtained my PhD in 2016 from Aix-Marseille University (AMU) in France, where I worked in the Qarma team (Machine Learning and Multimedia) under the supervision of François Denis and Hachem Kadri. I also obtained my MSc in fundamental computer science and my BSc in computer science from AMU. I am interested in tensor methods for machine learning and in designing learning algorithms for structured data by leveraging linear and multilinear algebra (e.g., spectral methods).

Current Students

Jun Dai

Postdoctorate - Université de Montréal

jun.dai@mila.quebec

alireza.dizaji@mila.quebec

Alireza Dizaji

Collaborating Alumni - Université de Montréal

Github

marawan.gamal@mila.quebec

Marawan Gamal

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Jian Tang

farzaneh.heidari@mila.quebec

Collaborating researcher - McGill University

Principal supervisor :

PhD - Université de Montréal

lizairem@mila.quebec

charlotte.noxon@mila.quebec

Sitao Luan

Postdoctorate - McGill University

Co-supervisor :

Larry Ma

Research Intern - Polytechnique Montréal

maning.hust@gmail.com

Ewan Murphy

Collaborating researcher - INRIA

ewan.murphy@mila.quebec

Github

Charlotte Noxon

Master's Research - Université de Montréal

michael.rizvi-martel@mila.quebec

Michael Rizvi-Martel

PhD - Université de Montréal

Co-supervisor :

Adam M. Oberman

Github

pascal.tikeng@mila.quebec

Pascal Tikeng Notsawo

PhD - Université de Montréal

Co-supervisor :

Guillaume Dumas

Collaborating researcher - Université de Montréal

Co-supervisor :

Reihaneh Rabbany

aaron.tjandra@mila.quebec

Beheshteh Toloueirakhshan

PhD - Université de Montréal

rakhshab@mila.quebec

Publications

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets (Ultra Large Dataset)

Dominique Beaini

Shenyang Huang

Joao Alex Cunha

Zhiyi Li

Gabriela Moisescu-Pareja

Oleksandr Dymov

Samuel Maddrell-Mander

Callum McLean

Ali Parviz

Luis T. Díaz Müller

Jama Hussein Mohamud

Michael Craig

Cristian Gabellini

Jian Tang … (see 8 more)

Christopher G. Morris

Mirco Ravanelli

Guy Wolf

Prudencio Tossou

Hadrien Mary

Błażej Banaszewski

Chad Martin

Dominic Masters

2023-09-21

Zenodo (unknown)

Preface

François Coste

Faissal Ouardi

2023-07-04

Proceedings of 16th edition of the International Conference on Grammatical Inference (published)

proceedings.mlr.press

ROSA: Random Orthogonal Subspace Adaptation

2023-06-19

ICML.cc/2023/Workshop/ES-FoMO (poster)

openreview.net

Fast and Attributed Change Detection on Dynamic Graphs with Density of States

2023-05-14

arXiv (preprint)

arxiv.org

Benchmarking State-Merging Algorithms for Learning Regular Languages.

Adil Soubki

Jeffrey Heinz

François Coste

Faissal Ouardi

2022-12-31

International Conference on Graphics and Interaction (published)

Explaining Graph Neural Networks Using Interpretable Local Surrogates

Farzaneh Heidari

Perouz Taslakian

2022-12-31

TAG-ML (published)

proceedings.mlr.press

Formal and Empirical Studies of Counting Behaviour in ReLU RNNs.

Nadine El-Naggar

Andrew Ryzhikov

Laure Daviaud

Pranava Madhyastha

Tillman Weyde

François Coste

Faissal Ouardi

2022-12-31

International Conference on Graphics and Interaction (published)

Identification of Substitutable Context-Free Languages over Infinite Alphabets from Positive Data

Yutaro Numaya

Diptarama Hendrian

Ryo Yoshinaka

Ayumi Shinohara

François Coste

Faissal Ouardi

This paper is concerned with the identification in the limit from positive data of sub-stitutable context-free languages cfl s) over infinit… (see more)e alphabets. Clark and Eyraud (2007) showed that substitutable cfl s over finite alphabets are learnable in this learning paradigm. We show that substitutable cfl s generated by grammars whose production rules may have predicates that represent sets of potentially infinitely many terminal symbols in a compact manner are learnable if the terminal symbol sets represented by those predicates are learnable, under a certain condition. This can be seen as a result parallel to Argyros and D’Antoni’s work (2018) that amplifies the query learnability of predicate classes to that of symbolic automata classes. Our result is the first that shows such amplification is possible for identifying some cfl s in the limit from positive data.

2022-12-31

ICGI (published)

Learning Syntactic Monoids from Samples by extending known Algorithms for learning State Machines

Simon Dieck

Sicco Verwer

François Coste

Faissal Ouardi

For the inference of regular languages, most current methods learn a version of deterministic finite automata. Syntactic monoids are an alte… (see more)rnative representation of regular languages, which have some advantages over automata. For example, traces can be parsed starting from any index and the star-freeness of the language they represent can be checked in polynomial time. But, to date, there existed no passive learning algorithm for syntactic monoids. In this paper, we prove that known state-merging algorithms for learning deterministic finite automata can be instrumented to learn syntactic monoids instead, by using as the input a special structure proposed in this paper: the interfix-graph. Further, we introduce a method to encode frequencies on the interfix-graph, such that models can also be learned from only positive traces. We implemented this structure and performed experiments with both traditional data and data containing only positive traces. As such this work answers basic theoretical and experimental questions regarding a novel passive learning algorithm for syntactic monoids.

2022-12-31

International Conference on Graphics and Interaction (published)

Lower Bounds for Active Automata Learning.

Loes Kruger

Bharat Garhewal

François Coste

Frits W. Vaandrager

Faissal Ouardi

2022-12-31

ICGI (published)

Spectral Regularization: an Inductive Bias for Sequence Modeling

Kaiwen Hou

Hou Rabusseau

2022-11-03

ArXiv (preprint)

arxiv.org

Sequential Density Estimation via NCWFAs Sequential Density Estimation via Nonlinear Continuous Weighted Finite Automata

Tianyu Li

Bogdan Mazoure

Weighted finite automata (WFAs) have been widely applied in many fields. One of the classic problems for WFAs is probability distribution es… (see more)timation over sequences of discrete symbols. Although WFAs have been extended to deal with continuous input data, namely continuous WFAs (CWFAs), it is still unclear how to approximate density functions over sequences of continuous random variables using WFA-based models, due to the limitation on the expressiveness of the model as well as the tractability of approximating density functions via CWFAs. In this paper, we propose a nonlinear extension to the CWFA model to first improve its expressiveness, we refer to it as the nonlinear continuous WFAs (NCWFAs). Then we leverage the so-called RNADE method, which is a well-known density estimator based on neural networks, and propose the RNADE-NCWFA model. The RNADE-NCWFA model computes a density function by design. We show that this model is strictly more expressive than the Gaussian HMM model, which CWFA cannot approximate. Empirically, we conduct a synthetic experiment using Gaussian HMM generated data. We focus on evaluating the model's ability to estimate densities for sequences of varying lengths (longer length than the training data). We observe that our model performs the best among the compared baseline methods.

2022-06-07

arXiv (preprint)