Publications

(Oral) Symmetry breaking and equivariant neural networks
Sékou-Oumar Kaba, Siamak Ravanbakhsh
NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations, 2023

Equivariant adaptation of large pre-trained models
Arnab Kumar Mondal*, Siba Smarak Panigrahi*, Sékou-Oumar Kaba, Sai Rajeswar, Siamak Ravanbakhsh
Advances in Neural Information Processing Systems (NeurIPS), 2023
arXiv:2310.01647

Equivariance with learned canonicalization functions
Sékou-Oumar Kaba*, Arnab Kumar Mondal*, Yan Zhang, Yoshua Bengio, Siamak Ravanbakhsh
International Conference on Machine Learning (ICML), 2023
arXiv:2211.06489

Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
Daniel Levy*, Sékou-Oumar Kaba*, Carmelo Gonzales, Santiago Miret, Siamak Ravanbakhsh
International Conference on Machine Learning (ICML), 2023
arXiv:2211.06489

Prediction of large magnetic moment materials with graph neural networks and random forests
Sékou-Oumar Kaba, Benjamin Groleau-Paré, Marc-Antoine Gauthier, A-MS Tremblay, Simon Verret, Chloé Gauvin-Ndiaye
Physical Review Materials
arXiv:2111.14712

Equivariant networks for crystal structures
Sékou-Oumar Kaba, Siamak Ravanbakhsh
Advances in Neural Information Processing Systems (NeurIPS), 2022
arXiv:2211.15420

(Spotlight) Equivariance with learned canonicalization functions
Sékou-Oumar Kaba*, Arnab Kumar Mondal*, Yan Zhang, Yoshua Bengio, Siamak Ravanbakhsh
NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations, 2022
arXiv:2211.06489

Gradient starvation: A learning proclivity in neural networks
Mohammad Pezeshki, Sékou-Oumar Kaba, Yoshua Bengio, Aaron Courville, Doina Precup, Guillaume Lajoie
Advances in Neural Information Processing Systems (NeurIPS), 2021
arXiv:2011.09468

Group-theoretical classification of superconducting states of strontium ruthenate
Sékou-Oumar Kaba, David Sénéchal
Physical Review B, 100 (21), 214507, 2019
arXiv:1905.10467