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

Alireza Dizaji

Collaborating Alumni - Université de Montréal

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Collaborating Alumni - McGill University

Principal supervisor :

Collaborating researcher - Université de Montréal

Maude Lizaire

PhD - Université de Montréal

Sitao Luan

Postdoctorate - McGill University

Co-supervisor :

Ewan Murphy

Collaborating researcher - INRIA

Charlotte Noxon

Master's Research - Université de Montréal

Soroush Omranpour

Collaborating Alumni - McGill University

Principal supervisor :

Michael Rizvi-Martel

PhD - Université de Montréal

Co-supervisor :

Pascal Tikeng Notsawo

PhD - Université de Montréal

Co-supervisor :

Collaborating researcher - Université de Montréal

Co-supervisor :

Website

Beheshteh Toloueirakhshan

PhD - Université de Montréal

Website

Publications

T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs

Alireza Dizaji

Benedict Aaron Tjandra

Mehrab Hamidi

Shenyang Huang

Dynamic graph learning methods have recently emerged as powerful tools for modelling relational data evolving through time. However, despite… (see more) extensive benchmarking efforts, it remains unclear whether current Temporal Graph Neural Networks (TGNNs) effectively capture core temporal patterns such as periodicity, cause-and-effect, and long-range dependencies. In this work, we introduce the Temporal Graph Reasoning Benchmark (T-GRAB), a comprehensive set of synthetic tasks designed to systematically probe the capabilities of TGNNs to reason across time. T-GRAB provides controlled, interpretable tasks that isolate key temporal skills: counting/memorizing periodic repetitions, inferring delayed causal effects, and capturing long-range dependencies over both spatial and temporal dimensions. We evaluate 11 temporal graph learning methods on these tasks, revealing fundamental shortcomings in their ability to generalize temporal patterns. Our findings offer actionable insights into the limitations of current models, highlight challenges hidden by traditional real-world benchmarks, and motivate the development of architectures with stronger temporal reasoning abilities. The code for T-GRAB can be found at: https://github.com/alirezadizaji/T-GRAB.

2025-06-25

MLoG-GenAI @ ACM SIGKDD Conference on Knowledge Discovery and Data Mining (oral)

TGM: A Modular Framework for Machine Learning on Temporal Graphs

Michael M. Bronstein

Matthias Fey

While deep learning on static graphs has been revolutionized by standardized libraries like PyTorch Geometric and DGL, machine learning on T… (see more)emporal Graphs (TG), networks that evolve over time, lacks comparable software infrastructure. Existing TG libraries are limited in scope, focusing on a single method category or specific algorithms. We introduce Temporal Graph Modelling (TGM), a comprehensive framework for machine learning on temporal graphs to address this gap. Through a modular architecture, TGM is the first library to support both discrete and continuous-time TG methods and implements a wide range of TG methods. The TGM framework combines an intuitive front-end API with an optimized backend storage, enabling reproducible research and efficient experimentation at scale. Key features include graph-level optimizations for offline training and built-in performance profiling capabilities. Through extensive benchmarking on five real-world networks, TGM is up to 6 times faster than the widely used DyGLib library on TGN and TGAT models and up to 8 times faster than the UTG framework for converting edges into coarse-grained snapshots.

2025-06-08

ICML.cc/2025/Workshop/CODEML (published)

RL Fine-Tuning Heals OOD Forgetting in SFT

Sicheng Lyu

Mohammad Hamdaqa

The two-stage fine-tuning paradigm of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has empirically shown better reas… (see more)oning performance than one-stage SFT for the post-training of Large Language Models (LLMs). However, the evolution and mechanism behind the synergy of SFT and RL are still under-explored and inconclusive. In our study, we find the well-known claim "SFT memorizes, RL generalizes" is over-simplified, and discover that: (1) OOD performance peaks at the early stage of SFT and then declines (OOD forgetting), the best SFT checkpoint cannot be captured by training/test loss; (2) the subsequent RL stage does not generate fundamentally better OOD capability, instead it plays an \textbf{OOD restoration} role, recovering the lost reasoning ability during SFT; (3) The recovery ability has boundaries, \ie{} \textbf{if SFT trains for too short or too long, RL cannot recover the lost OOD ability;} (4) To uncover the underlying mechanisms behind the forgetting and restoration process, we employ SVD analysis on parameter matrices, manually edit them, and observe their impacts on model performance. Unlike the common belief that the shift of model capacity mainly results from the changes of singular values, we find that they are actually quite stable throughout fine-tuning. Instead, the OOD behavior strongly correlates with the \textbf{rotation of singular vectors}. Our findings re-identify the roles of SFT and RL in the two-stage fine-tuning and discover the rotation of singular vectors as the key mechanism. %reversing the rotations induced by SFT, which shows recovery from forgetting, whereas imposing the SFT parameter directions onto a RL-tuned model results in performance degradation. Code is available at https://github.com/xiaodanguoguo/RL_Heals_SFT

2024-12-31

arXiv (preprint)

arxiv.org

Higher Order Transformers: Enhancing Stock Movement Prediction On Multimodal Time-Series Data

Soroush Omranpour

In this paper, we tackle the challenge of predicting stock movements in financial markets by introducing Higher Order Transformers, a novel … (see more)architecture designed for processing multivariate time-series data. We extend the self-attention mechanism and the transformer architecture to a higher order, effectively capturing complex market dynamics across time and variables. To manage computational complexity, we propose a low-rank approximation of the potentially large attention tensor using tensor decomposition and employ kernel attention, reducing complexity to linear with respect to the data size. Additionally, we present an encoder-decoder model that integrates technical and fundamental analysis, utilizing multimodal signals from historical prices and related tweets. Our experiments on the Stocknet dataset demonstrate the effectiveness of our method, highlighting its potential for enhancing stock movement prediction in financial markets.

2024-12-12

ArXiv (preprint)

arxiv.org

GFlowNets for Hamiltonian decomposition in groups of compatible operators

Isaac L. Huidobro-Meezs

Jun Dai

R. A. Vargas-Hern'andez

Quantum computing presents a promising alternative for the direct simulation of quantum systems with the potential to explore chemical probl… (see more)ems beyond the capabilities of classical methods. However, current quantum algorithms are constrained by hardware limitations and the increased number of measurements required to achieve chemical accuracy. To address the measurement challenge, techniques for grouping commuting and anti-commuting terms, driven by heuristics, have been developed to reduce the number of measurements needed in quantum algorithms on near-term quantum devices. In this work, we propose a probabilistic framework using GFlowNets to group fully (FC) or qubit-wise commuting (QWC) terms within a given Hamiltonian. The significance of this approach is demonstrated by the reduced number of measurements for the found groupings; 51% and 67% reduction factors respectively for FC and QWC partitionings with respect to greedy coloring algorithms, highlighting the potential of GFlowNets for future applications in the measurement problem. Furthermore, the flexibility of our algorithm extends its applicability to other resource optimization problems in Hamiltonian simulation, such as circuit design.

2024-10-20

ArXiv (preprint)

arxiv.org

TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs

Erfan Loghmani

Emanuele Rossi

Ioannis Koutis

Heiner Stuckenschmidt

Multi-relational temporal graphs are powerful tools for modeling real-world data, capturing the evolving and interconnected nature of entiti… (see more)es over time. Recently, many novel models are proposed for ML on such graphs intensifying the need for robust evaluation and standardized benchmark datasets. However, the availability of such resources remains scarce and evaluation faces added complexity due to reproducibility issues in experimental protocols. To address these challenges, we introduce Temporal Graph Benchmark 2.0 (TGB 2.0), a novel benchmarking framework tailored for evaluating methods for predicting future links on Temporal Knowledge Graphs and Temporal Heterogeneous Graphs with a focus on large-scale datasets, extending the Temporal Graph Benchmark. TGB 2.0 facilitates comprehensive evaluations by presenting eight novel datasets spanning five domains with up to 53 million edges. TGB 2.0 datasets are significantly larger than existing datasets in terms of number of nodes, edges, or timestamps. In addition, TGB 2.0 provides a reproducible and realistic evaluation pipeline for multi-relational temporal graphs. Through extensive experimentation, we observe that 1) leveraging edge-type information is crucial to obtain high performance, 2) simple heuristic baselines are often competitive with more complex methods, 3) most methods fail to run on our largest datasets, highlighting the need for research on more scalable methods.

2024-09-25

Datasets and Benchmarks Track @ Neural Information Processing Systems (poster)

Efficient Leverage Score Sampling for Tensor Train Decomposition

Vivek Bharadwaj

Beheshteh T. Rakhshan

Osman Asif Malik

Tensor Train~(TT) decomposition is widely used in the machine learning and quantum physics communities as a popular tool to efficiently comp… (see more)ress high-dimensional tensor data. In this paper, we propose an efficient algorithm to accelerate computing the TT decomposition with the Alternating Least Squares (ALS) algorithm relying on exact leverage scores sampling. For this purpose, we propose a data structure that allows us to efficiently sample from the tensor with time complexity logarithmic in the tensor size. Our contribution specifically leverages the canonical form of the TT decomposition. By maintaining the canonical form through each iteration of ALS, we can efficiently compute (and sample from) the leverage scores, thus achieving significant speed-up in solving each sketched least-square problem. Experiments on synthetic and real data on dense and sparse tensors demonstrate that our method outperforms SVD-based and ALS-based algorithms.

2024-09-24

NeurIPS.cc/2024/Conference (poster)

MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs

Razieh Shirzadkhani

Tran Gia Bao Ngo

Kiarash Shamsi

Poupak Azad

Baris Coskunuzer

Cuneyt Gurcan Akcora

2024-06-13

ArXiv (preprint)

A Tensor Decomposition Perspective on Second-order RNNS

Maude Lizaire

Michael Rizvi-Martel

Marawan Gamal Abdel Hameed

Second-order Recurrent Neural Networks (2RNNs) extend RNNs by leveraging second-order interactions for sequence modelling. These models are … (see more)provably more expressive than their first-order counterparts and have connections to well-studied models from formal language theory. However, their large parameter tensor makes computations intractable. To circumvent this issue, one approach known as MIRNN consists in limiting the type of interactions used by the model. Another is to leverage tensor decomposition to diminish the parameter count. In this work, we study the model resulting from parameterizing 2RNNs using the CP decomposition, which we call CPRNN. Intuitively, the rank of the decomposition should reduce expressivity. We analyze how rank and hidden size affect model capacity and show the relationships between RNNs, 2RNNs, MIRNNs, and CPRNNs based on these parameters. We support these results empirically with experiments on the Penn Treebank dataset which demonstrate that, with a fixed parameter budget, CPRNNs outperforms RNNs, 2RNNs, and MIRNNs with the right choice of rank and hidden size.

2024-04-30

ICML.cc/2024/Conference (spotlight)

proceedings.mlr.press

Length Independent PAC-Bayes Bounds for Simple RNNs

Volodimir Mitarchuk

Clara Lacroce

Rémi Eyraud

Rémi Emonet

Amaury Habrard

2024-04-17

Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)

proceedings.mlr.press

Simulating Weighted Automata over Sequences and Trees with Transformers

Michael Rizvi

Maude Lizaire

Clara Lacroce

Transformers are ubiquitous models in the natural language processing (NLP) community and have shown impressive empirical successes in the p… (see more)ast few years. However, little is understood about how they reason and the limits of their computational capabilities. These models do not process data sequentially, and yet outperform sequential neural models such as RNNs. Recent work has shown that these models can compactly simulate the sequential reasoning abilities of deterministic finite automata (DFAs). This leads to the following question: can transformers simulate the reasoning of more complex finite state machines? In this work, we show that transformers can simulate weighted finite automata (WFAs), a class of models which subsumes DFAs, as well as weighted tree automata (WTA), a generalization of weighted automata to tree structured inputs. We prove these claims formally and provide upper bounds on the sizes of the transformer models needed as a function of the number of states the target automata. Empirically, we perform synthetic experiments showing that transformers are able to learn these compact solutions via standard gradient-based training.

2024-04-17

Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)

proceedings.mlr.press

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets

Dominique Beaini

Shenyang Huang

Joao Alex Cunha

Zhiyi Li

Gabriela Moisescu-Pareja

Oleksandr Dymov

Samuel Maddrell-Mander

Callum McLean

Jama Hussein Mohamud

Michael Craig

Cristian Gabellini

Kerstin Klasers

Josef Dean

Cas Wognum … (see 15 more)

Maciej Sypetkowski

Ioannis Koutis

Hadrien Mary

Therence Bois

Andrew Fitzgibbon

Błażej Banaszewski

Chad Martin

Dominic Masters

Recently, pre-trained foundation models have shown significant advancements in multiple fields. However, the lack of datasets with labeled f… (see more)eatures and codebases has hindered the development of a supervised foundation model for molecular tasks. Here, we have carefully curated seven datasets specifically tailored for node- and graph-level prediction tasks to facilitate supervised learning on molecules. Moreover, to support the development of multi-task learning on our proposed datasets, we created the Graphium graph machine learning library. Our dataset collection encompasses two distinct categories. Firstly, the TOYMIX category modifies three small existing datasets with additional data for multi-task learning. Secondly, the LARGEMIX category includes four large-scale datasets with 344M graph-level data points and 409M node-level data points from ∼5M unique molecules. Finally, the ultra-large dataset contains 2,210M graph-level data points and 2,031M node-level data points coming from 86M molecules. Hence our datasets represent an order of magnitude increase in data volume compared to other 2D-GNN datasets. In addition, recognizing that molecule-related tasks often span multiple levels, we have designed our library to explicitly support multi-tasking, offering a diverse range of multi-level representations, i.e., representations at the graph, node, edge, and node-pair level. We equipped the library with an extensive collection of models and features to cover different levels of molecule analysis. By combining our curated datasets with this versatile library, we aim to accelerate the development of molecule foundation models. Datasets and code are available at https://github.com/datamol-io/graphium.

2024-01-15

ICLR.cc/2024/Conference (poster)