Portrait of Guillaume Rabusseau

Guillaume Rabusseau

Core Academic Member
rabussgu@mila.quebec
Canada CIFAR AI Chair
Assistant Professor, Université de Montréal, Department of Computer Science and Operations Research
Research Topics
Deep Learning
Graph Neural Networks
Learning on Graphs
Machine Learning Theory
Probabilistic Models
Quantum Information Theory
Recommender Systems
Recurrent Neural Networks
Tensor Factorization
Website
Google Scholar

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
Google Scholar
Alireza Dizaji
Master's Research - Université de Montréal
Github
Google Scholar
Marawan Gamal
PhD - Université de Montréal
Website
Github
Google Scholar
Farzana Heidari
PhD - Université de Montréal
Co-supervisor :
Jian Tang
Website
Github
Google Scholar
Shenyang Huang
Collaborating Alumni - McGill University
Principal supervisor :
Reihaneh Rabbany
Website
Github
Google Scholar
Chelsea John
Independent visiting researcher - Technical University of Hambrug, Germany
Website
Github
Google Scholar
Damien Lessens
Collaborating researcher - Université de Montréal
Github
Maude Lizaire
PhD - Université de Montréal
Google Scholar
Sitao Luan
Postdoctorate - McGill University
Co-supervisor :
Reihaneh Rabbany
Github
Google Scholar
Charlotte Noxon
Master's Research - Université de Montréal
Google Scholar
Soroush Omranpour
Collaborating researcher - McGill University
Principal supervisor :
Reihaneh Rabbany
Github
Michael Rizvi-Martel
PhD - Université de Montréal
Co-supervisor :
Adam M. Oberman
Website
Github
Google Scholar
Pascal Tikeng Notsawo
PhD - Université de Montréal
Co-supervisor :
Guillaume Dumas
Website
Github
Google Scholar
Aaron Tjandra
Collaborating researcher - Université de Montréal
Co-supervisor :
Reihaneh Rabbany
Website
Google Scholar
Beheshteh Toloueirakhshan
PhD - Université de Montréal
Website

Publications

Neural Network Based Nonlinear Weighted Finite Automata
Tianyu Li
Guillaume Rabusseau
Doina Precup
Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models. Given the recent succ… (see more)esses of nonlinear models in machine learning, it is natural to wonder whether ex-tending WFA to the nonlinear setting would be beneficial. In this paper, we propose a novel model of neural network based nonlinearWFA model (NL-WFA) along with a learning algorithm. Our learning algorithm is inspired by the spectral learning algorithm for WFAand relies on a nonlinear decomposition of the so-called Hankel matrix, by means of an auto-encoder network. The expressive power of NL-WFA and the proposed learning algorithm are assessed on both synthetic and real-world data, showing that NL-WFA can lead to smaller model sizes and infer complex grammatical structures from data.
2017-09-13
ArXiv (preprint)
arxiv.org
arxiv.org
Hierarchical Methods of Moments
Matteo Ruffini
Guillaume Rabusseau
Borja Balle
Spectral methods of moments provide a powerful tool for learning the parameters of latent variable models. Despite their theoretical appeal,… (see more) the applicability of these methods to real data is still limited due to a lack of robustness to model misspecification. In this paper we present a hierarchical approach to methods of moments to circumvent such limitations. Our method is based on replacing the tensor decomposition step used in previous algorithms with approximate joint diagonalization. Experiments on topic modeling show that our method outperforms previous tensor decomposition methods in terms of speed and model quality.
arxiv.org
Multitask Spectral Learning of Weighted Automata
Guillaume Rabusseau
Borja Balle
Joelle Pineau
We consider the problem of estimating multiple related functions computed by weighted automata~(WFA). We first present a natural notion of r… (see more)elatedness between WFAs by considering to which extent several WFAs can share a common underlying representation. We then introduce the model of vector-valued WFA which conveniently helps us formalize this notion of relatedness. Finally, we propose a spectral learning algorithm for vector-valued WFAs to tackle the multitask learning problem. By jointly learning multiple tasks in the form of a vector-valued WFA, our algorithm enforces the discovery of a representation space shared between tasks. The benefits of the proposed multitask approach are theoretically motivated and showcased through experiments on both synthetic and real world datasets.