CRAFT: Concept Recursive Activation FacTorization for Explainability T Fel, A Picard, L Bethune, T Boissin, D Vigouroux, J Colin, R Cadène, ... IEEE / CVF Computer Vision and Pattern Recognition (CVPR 2023), 2023 | 54 | 2023 |
Pay attention to your loss: understanding misconceptions about lipschitz neural networks L Béthune, T Boissin, M Serrurier, F Mamalet, C Friedrich, ... Advances in Neural Information Processing Systems 35, 20077-20091, 2022 | 35* | 2022 |
Xplique: A deep learning explainability toolbox T Fel, L Hervier, D Vigouroux, A Poche, J Plakoo, R Cadene, M Chalvidal, ... arXiv preprint arXiv:2206.04394, 2022 | 25 | 2022 |
A holistic approach to unifying automatic concept extraction and concept importance estimation T Fel, V Boutin, L Béthune, R Cadène, M Moayeri, L Andéol, M Chalvidal, ... Advances in Neural Information Processing Systems 36, 2024 | 13 | 2024 |
Predicting the generalization ability of a few-shot classifier M Bontonou, L Béthune, V Gripon Information 12 (1), 29, 2021 | 11* | 2021 |
Gaussian processes on distributions based on regularized optimal transport F Bachoc, L Béthune, A Gonzalez-Sanz, JM Loubes International Conference on Artificial Intelligence and Statistics, 4986-5010, 2023 | 10 | 2023 |
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective M Serrurier, F Mamalet, T Fel, L Béthune, T Boissin Advances in Neural Information Processing Systems 36, 2024 | 9* | 2024 |
Ranking deep learning generalization using label variation in latent geometry graphs C Lassance, L Béthune, M Bontonou, M Hamidouche, V Gripon arXiv preprint arXiv:2011.12737, 2020 | 9 | 2020 |
Hierarchical and unsupervised graph representation learning with loukas’s coarsening L Béthune, Y Kaloga, P Borgnat, A Garivier, A Habrard Algorithms 13 (9), 206, 2020 | 7 | 2020 |
Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks Louis Bethune, Paul Novello, Thibaut Boissin, Guillaume Coiffier, Mathieu ... International Conference on Machine Learning (ICML 2023), 2023 | 4* | 2023 |
DP-SGD Without Clipping: The Lipschitz Neural Network Way L Béthune, T Masséna, T Boissin, Y Prudent, C Friedrich, F Mamalet, ... International Conference on Learning Representations (ICLR 2024), 2024 | 3 | 2024 |
Gan estimation of lipschitz optimal transport maps A González-Sanz, L De Lara, L Béthune, JM Loubes arXiv preprint arXiv:2202.07965, 2022 | 2 | 2022 |
Certifiable Metric One Class Learning with adversarially trained Lipschitz Classifier L Béthune, M Serrurier NeurIPS ML Safety Workshop, 2022 | 1 | 2022 |
Deep Sturm–Liouville: Learnable orthogonal basis functions parameterized by neural networks D Vigouroux, J Dalmau, L Béthune | | 2024 |
1-Lipschitz Neural Distance Fields G Coiffier, L Béthune The Eurographics Association and John Wiley & Sons Ltd., 2024 | | 2024 |
TaCo: Targeted Concept Removal in Output Embeddings for NLP via Information Theory and Explainability F Jourdan, L Béthune, A Picard, L Risser, N Asher arXiv preprint arXiv:2312.06499, 2023 | | 2023 |
Improved learning theory for kernel distribution regression with two-stage sampling F Bachoc, L Béthune, A González-Sanz, JM Loubes arXiv preprint arXiv:2308.14335, 2023 | | 2023 |
Efficient circuit implementation for coined quantum walks on binary trees and application to reinforcement learning T Mullor, D Vigouroux, L Bethune 2022 IEEE/ACM 7th Symposium on Edge Computing (SEC), 436-443, 2022 | | 2022 |