Articles in Peer-Reviewed Journals

B. Balle and G. Rabusseau. Approximate minimization of weighted tree automata. Information and Computation, 282:104654, 2022. [ bib | pdf ]
T. Li, D. Precup, and G. Rabusseau. Connecting weighted automata, tensor networks and recurrent neural networks through spectral learning. Machine Learning, 2022. [ bib | arXiv ]
B. Mazoure, T. Doan, T. Li, V. Makarenkov, J. Pineau, D. Precup, and G. Rabusseau. Low-rank representation of reinforcement learning policies. Journal of Artificial Intelligence Research, 2022. [ bib ]
V. Makarenkov, B. Mazoure, G. Rabusseau, and P. Legendre. Horizontal gene transfer and recombination analysis of sars-cov-2 genes helps discover its close relatives and shed light on its origin. BMC Ecology and Evolution, 21(1):1--18, 2021. [ bib ]
R. Bailly, G. Rabusseau, and F. Denis. Recognizable series on graphs and hypergraphs. Journal of Computer and System Sciences, 104:58 -- 81, 2019. [ bib | preprint | pdf ]
V. François-Lavet, G. Rabusseau, J. Pineau, D. Ernst, and R. Fonteneau. On overfitting and asymptotic bias in batch reinforcement learning with partial observability. Journal of Artificial Intelligence Research, 65:1--30, 2019. [ bib | arXiv ]

Articles in Peer-Reviewed International Conferences

S. Huang, J. Danovitch, G. Rabusseau, and R. Rabbany. Fast and attributed change detection on dynamic graphs with density of states. In PAKDD, 2023. [ bib | arXiv ]
S. Huang, F. Poursafaei, J. Danovitch, M. Fey, W. Hu, E. Rossi, J. Leskovec, M. Bronstein, G. Rabusseau, and R. Rabbany. Temporal graph benchmark for machine learning on temporal graphs. In NeurIPS, 2023. [ bib | arXiv ]
C. Hua, G. Rabusseau, and J. Tang. High-order pooling for graph neural networks with tensor decomposition. In NeurIPS, 2022. [ bib | arXiv ]
J. Miller, G. Rabusseau, and J. Terilla. Tensor networks for probabilistic sequence modeling. In AISTATS, 2021. [ bib | arXiv ]
T. Doan, M. Bennani, B. Mazoure, G. Rabusseau, and P. Alquier. A theoretical analysis of catastrophic forgetting through the NTK overlap matrix. In AISTATS, 2021. [ bib | arXiv ]
S. Srinivasan, S. Adhikary, J. Miller, G. Rabusseau, and B. Boots. Quantum tensor networks, stochastic processes, and weighted automata. In AISTATS, 2021. [ bib | arXiv ]
B. Balle, C. Lacroce, P. Panangaden, D. Precup, and G. Rabusseau. Optimal spectral-norm approximate minimization of weighted finite automata. In ICALP, 2021. [ bib | arXiv ]
S. Huang, V. François-Lavet, and G. Rabusseau. Understanding capacity saturation in incremental learning. In 34th Canadian Conference on Artificial Intelligence, 2021. [ bib ]
C. Lacroce, P. Panangaden, and G. Rabusseau. Extracting weighted automata for approximate minimization in language modelling. In ICGI, 2021. [ bib | arXiv ]
B. Khavari and G. Rabusseau. Lower and upper bounds on the pseudo-dimension of tensor network models. In NeurIPS, 2021. [ bib | arXiv ]
T. Li, B. Mazoure, D. Precup, and G. Rabusseau. Efficient planning under partial observability with unnormalized Q functions and spectral learning. AISTATS, 2020. [ bib | arXiv ]
B. Rakhshan and G. Rabusseau. Tensorized random projections. AISTATS, 2020. [ bib | code | arXiv ]
S. Huang, Y. Hitti, G. Rabusseau, and R. Rabbany. Laplacian change point detection for dynamic graphs. In KDD, 2020. [ bib | arXiv ]
G. Rabusseau, T. Li, and D. Precup. Connecting weighted automata and recurrent neural networks through spectral learning. In AISTATS, 2019. [ bib | arXiv | pdf | poster | slides ]
G. Rabusseau. Minimization of graph weighted models over circular strings. In FoSSaCS. 2018. [ bib | pdf | slides ]
T. Li, G. Rabusseau, and D. Precup. Nonlinear weighted finite automata. In AISTATS. 2018. [ bib | pdf ]
P. Amortila and G. Rabusseau. Learning graph weighted models on pictures. In ICGI, 2018. [ bib | arXiv | pdf ]
M. Ruffini, G. Rabusseau, and B. Balle. Hierarchical methods of moments. In NeurIPS. 2017. [ bib | pdf ]
G. Rabusseau, B. Balle, and J. Pineau. Multitask spectral learning of weighted automata. In NeurIPS. 2017. [ bib | pdf | poster | slides ]
G. Rabusseau, B. Balle, and S. B. Cohen. Low-Rank Approximation of Weighted Tree Automata. In AISTATS, 2016. [ bib | arXiv | pdf | poster ]
G. Rabusseau and H. Kadri. Low-rank regression with tensor responses. In NeurIPS. 2016. [ bib | code | pdf | poster ]
R. Bailly, F. Denis, and G. Rabusseau. Recognizable Series on Hypergraphs. In LATA, 2015. [ bib | arXiv | slides ]
G. Rabusseau and F. Denis. Maximizing a Tree Series in the Representation Space. In ICGI, 2014. [ bib | pdf | slides ]

Technical Reports / Preprints

M. Hashemizadeh, M. Liu, J. Miller, and G. Rabusseau. Adaptive tensor learning with tensor networks. arXiv preprint arXiv:2008.05437, 2020. [ bib | arXiv ]
S. Huang, V. François-Lavet, and G. Rabusseau. Neural architecture search for class-incremental learning. arXiv preprint arXiv:1909.06686, 2019. [ bib ]
X. Cao and G. Rabusseau. Tensor regression networks with various low-rank tensor approximations. arXiv preprint arXiv:1712.09520, 2017. [ bib | arXiv ]
G. Rabusseau and F. Denis. Learning Negative Mixture Models by Tensor Decompositions. CoRR, abs/1403.4224, 2014. [ bib | arXiv ]

Workshop Contributions

F. Heidari, P. Taslakian, and G. Rabusseau. Explaining graph neural networks using interpretable local surrogates. In Topological, Algebraic and Geometric Learning Workshops 2023, pages 146--155. PMLR, 2023. [ bib ]
M. Gamal and G. Rabusseau. Rosa: Random orthogonal subspace adaptation. In Workshop on Efficient Systems for Foundation Models@ ICML2023, 2023. [ bib ]
K. Hou and G. Rabusseau. Spectral regularization: an inductive bias for sequence modeling. LearnAut workshop at ICALP 2022, 2022. [ bib ]
M. Lizaire, S. Verret, and G. Rabusseau. Spectral initialization of recurrent neural networks: Proof of concept. LearnAut workshop at ICALP 2022, 2022. [ bib ]
T. Li, B. Mazoure, and G. Rabusseau. Sequential density estimation via ncwfas sequential density estimation via nonlinear continuous weighted finite automata. LearnAut workshop at ICALP 2022, 2022. [ bib ]
C. Lacroce, P. Panangaden, and G. Rabusseau. Towards an aak theory approach to approximate minimization in the multi-letter case. LearnAut workshop at ICALP 2022, 2022. [ bib ]
A. Huang, K.-C. Wang, G. Rabusseau, and A. Makhzani. Few shot image generation via implicit autoencoding of support sets. In Fifth Workshop on Meta-Learning at the Conference on Neural Information Processing Systems, 2021. [ bib ]
B. T. Rakhshan and G. Rabusseau. Rademacher random projections with tensor networks. In Second Workshop on Quantum Tensor Networks in Machine Learning In conjunction with NeurIPS, 2021. [ bib ]
S. Srinivasan, S. Adhikary, J. Miller, B. Pokharel, G. Rabusseau, and B. Boots. Towards a trace-preserving tensor network representation of quantum channels. In Second Workshop on Quantum Tensor Networks in Machine Learning In conjunction with NeurIPS, 2021. [ bib ]
P. Amortila and G. Rabusseau. Learning graph weighted models on pictures. 2nd workshop on Learning and Automata (LearnAut at FLoC 2018), 2018. [ bib ]
S. Huang, V. François-Lavet, G. Rabusseau, and J. Pineau. Exploring continual learning using incremental architecture search. NeurIPS 2018 Workshop on Continual Learning, 2018. [ bib | pdf ]
D. Wu, G. Rabusseau, V. François-lavet, D. Precup, and B. Boulet. Optimizing home energy management and electric vehicle charging with reinforcement learning. Adaptive Learning Agents (ALA) workshop at the Federated AI Meeting, 2018. [ bib | pdf ]
T. Li, G. Rabusseau, and D. Precup. Neural network based nonlinear weighted finite automata. LICS workshop on Learning and Automata, 2017. [ bib ]
G. Rabusseau and J. Pineau. Multitask spectral learning of weighted automata. LICS workshop on Learning and Automata, 2017. [ bib ]
R. Bailly and G. Rabusseau. Graph learning as a tensor factorization problem. NIPS workshop on Learning with Tensors, 2016. [ bib | pdf ]
G. Rabusseau and F. Denis. Learning Negative Mixture Models by Tensor Decompositions. Workshop on Method of Moments and Spectral Learning (ICML 2014), 2014. [ bib | poster ]

Thesis

G. Rabusseau. A Tensor Perspective on Weighted Automata, Low-Rank Regression and Algebraic Mixtures. PhD thesis, Aix-Marseille Université, 2016. [ bib | pdf ]