| Manifold Mixup: Better Representations by Interpolating Hidden States V Verma, A Lamb, C Beckham, A Najafi, I Mitliagkas, D Lopez-Paz, ... International Conference on Machine Learning, 6438-6447, 2019 | 1836 | 2019 |
| Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization FY Sun, J Hoffmann, V Verma, J Tang ICLR 2020 Spotlight, 2019 | 1386 | 2019 |
| Interpolation consistency training for semi-supervised learning V Verma, A Lamb, J Kannala, Y Bengio, D Lopez-Paz IJCAI 2019, 2019 | 1062 | 2019 |
| GraphMix: Improved Training of GNNs for Semi-Supervised Learning V Verma, M Qu, K Kawaguchi, A Lamb, Y Bengio, J Kannala, J Tang AAAI 2021, 2019 | 236 | 2019 |
| Residual connections encourage iterative inference S Jastrzębski, D Arpit, N Ballas, V Verma, T Che, Y Bengio ICLR 2018, 2017 | 198 | 2017 |
| Towards Domain-Agnostic Contrastive Learning V Verma, MT Luong, K Kawaguchi, H Pham, QV Le ICML2021, 2020 | 166 | 2020 |
| Interpolated adversarial training: Achieving robust neural networks without sacrificing too much accuracy A Lamb, V Verma, J Kannala, Y Bengio Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security …, 2019 | 129 | 2019 |
| Patchup: A regularization technique for convolutional neural networks M Faramarzi, M Amini, A Badrinaaraayanan, V Verma, S Chandar AAAI 2022, 2020 | 100* | 2020 |
| Interpolation-based semi-supervised learning for object detection J Jeong, V Verma, M Hyun, J Kannala, N Kwak CVPR 2021, 2020 | 92 | 2020 |
| On adversarial mixup resynthesis C Beckham, S Honari, V Verma, AM Lamb, F Ghadiri, RD Hjelm, Y Bengio, ... Advances in neural information processing systems, 4346-4357, 2019 | 86 | 2019 |
| On adversarial mixup resynthesis C Beckham, S Honari, V Verma, AM Lamb, F Ghadiri, RD Hjelm, Y Bengio, ... Advances in neural information processing systems, 4346-4357, 2019 | 86 | 2019 |
| Manifold mixup: Encouraging meaningful on-manifold interpolation as a regularizer V Verma, A Lamb, C Beckham, A Courville, I Mitliagkis, Y Bengio stat 1050, 13, 2018 | 65 | 2018 |
| Towards understanding generalization in gradient-based meta-learning S Guiroy, V Verma, C Pal arXiv preprint arXiv:1907.07287, 2019 | 24 | 2019 |
| Deep semi-random features for nonlinear function approximation K Kawaguchi, B Xie, V Verma, L Song Thirty-Second AAAI Conference on Artificial Intelligence, 2018 | 22 | 2018 |
| Manifold mixup: Learning better representations by interpolating hidden states V Verma, A Lamb, C Beckham, A Najafi, A Courville, I Mitliagkas, ... | 21 | 2018 |
| Towards understanding generalization via analytical learning theory K Kawaguchi, Y Bengio, V Verma, LP Kaelbling arXiv preprint arXiv:1802.07426, 2018 | 21* | 2018 |
| Method and apparatus for determining similarity information for users of a network V Verma US Patent 9,373,128, 2016 | 19 | 2016 |
| Mixupe: Understanding and improving mixup from directional derivative perspective Y Zou, V Verma, S Mittal, WH Tang, H Pham, J Kannala, Y Bengio, A Solin, ... Uncertainty in Artificial Intelligence, 2597-2607, 2023 | 13 | 2023 |
| Sketchtransfer: A new dataset for exploring detail-invariance and the abstractions learned by deep networks A Lamb, S Ozair, V Verma, D Ha Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2020 | 13 | 2020 |
| Modularity matters: learning invariant relational reasoning tasks J Jo, V Verma, Y Bengio arXiv preprint arXiv:1806.06765, 2018 | 11 | 2018 |
Yoshua BengioProfessor of computer science, University of Montreal, Mila, IVADO, CIFARVerified email at umontreal.ca
