Guillaume Rabusseau
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2019
Renewed Canada CIFAR AI Chair – 2024
Guillaume Rabusseau is associate professor in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal, core member of Mila and a Canada CIFAR AI Chair.
His research focuses on the intersection of machine learning, theoretical computer science and multilinear algebra. In particular, he specializes in exploring the connections between tensors, machine learning. He develops efficient learning schemes for structured data by leveraging linear and multi-linear algebra.
In general, he is interested in tensor decompositions techniques, using tensor networks for machine learning, quantum machine learning, kernel methods, (weighted) automata theory and non-linear computational models on strings, trees, and graphs.
Relevant Publications
- Lizaire, M., Rizvi-Martel, M., Hameed, M. G. A., & Rabusseau, G. (2024). A Tensor Decomposition Perspective on Second-order RNNs. ICML 2024.
- Huang, S., Poursafaei, F., Danovitch, J., Fey, M., Hu, W., Rossi, E., Leskovec, J., Bronstein, M., Rabusseau, G. and Rabbany, R., 2024. Temporal graph benchmark for machine learning on temporal graphs. Advances in Neural Information Processing Systems, 36.
- Hua, C., Rabusseau, G., & Tang, J., (2022). High-Order Pooling for Graph Neural Networks with Tensor Decomposition. Thirty-sixth Conference on Neural Information Processing Systems.
- Li, Tianyu, Doina Precup, and Guillaume Rabusseau. "Connecting weighted automata, tensor networks and recurrent neural networks through spectral learning." Machine Learning 113.5 (2022): 2619-2653.
Miller, J., Rabusseau, G., & Terilla, J. (2021). Tensor networks for probabilistic sequence modeling. In International Conference on Artificial Intelligence and Statistics (pp. 3079-3087). PMLR.