| How powerful are graph neural networks? K Xu, W Hu, J Leskovec, S Jegelka arXiv preprint arXiv:1810.00826, 2018 | 4417 | 2018 |
| Deep metric learning via lifted structured feature embedding H Oh Song, Y Xiang, S Jegelka, S Savarese Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2016 | 1568 | 2016 |
| Representation learning on graphs with jumping knowledge networks K Xu, C Li, Y Tian, T Sonobe, K Kawarabayashi, S Jegelka International Conference on Machine Learning, 5453-5462, 2018 | 1376 | 2018 |
| Max-value entropy search for efficient Bayesian optimization Z Wang, S Jegelka Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017 | 349 | 2017 |
| Deep Metric Learning via Facility Location HO Song, S Jegelka, V Rathod, K Murphy CVPR, 2017 | 332 | 2017 |
| Contrastive learning with hard negative samples J Robinson, SJ Chuang, Ching-Yao, Suvrit Sra International Conference on Learning Representations, 2021 | 322 | 2021 |
| Debiased contrastive learning CY Chuang, J Robinson, YC Lin, A Torralba, S Jegelka Advances in Neural Information Processing Systems 33, 2020 | 298 | 2020 |
| On learning to localize objects with minimal supervision HO Song, R Girshick, S Jegelka, J Mairal, Z Harchaoui, T Darrell International Conference on Machine Learning (ICML), 2014 | 281 | 2014 |
| Submodularity beyond submodular energies: coupling edges in graph cuts S Jegelka, J Bilmes Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on …, 2011 | 230 | 2011 |
| How neural networks extrapolate: From feedforward to graph neural networks K Xu, M Zhang, J Li, SS Du, K Kawarabayashi, S Jegelka arXiv preprint arXiv:2009.11848, 2020 | 200 | 2020 |
| Resnet with one-neuron hidden layers is a universal approximator H Lin, S Jegelka Advances in neural information processing systems 31, 6169-6178, 2018 | 192 | 2018 |
| Weakly-supervised discovery of visual pattern configurations HO Song, YJ Lee, S Jegelka, T Darrell Advances in neural information processing systems 27, 1637-1645, 2014 | 190 | 2014 |
| Generalization and representational limits of graph neural networks V Garg, S Jegelka, T Jaakkola International Conference on Machine Learning, 3419-3430, 2020 | 187 | 2020 |
| What Can Neural Networks Reason About? K Xu, J Li, M Zhang, SS Du, K Kawarabayashi, S Jegelka arXiv preprint arXiv:1905.13211, 2019 | 183 | 2019 |
| Batched large-scale bayesian optimization in high-dimensional spaces Z Wang, C Gehring, P Kohli, S Jegelka International Conference on Artificial Intelligence and Statistics, 745-754, 2018 | 149 | 2018 |
| Fast semidifferential-based submodular function optimization R Iyer, S Jegelka, J Bilmes International Conference on Machine Learning (ICML), 2013 | 132 | 2013 |
| Virtual screening of inorganic materials synthesis parameters with deep learning E Kim, K Huang, S Jegelka, E Olivetti npj Computational Materials 3 (53), 2017 | 114 | 2017 |
| Curvature and optimal algorithms for learning and minimizing submodular functions RK Iyer, S Jegelka, JA Bilmes Advances in Neural Information Processing Systems 26, 2742-2750, 2013 | 107 | 2013 |
| Batched high-dimensional bayesian optimization via structural kernel learning Z Wang, C Li, S Jegelka, P Kohli Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017 | 105 | 2017 |
| Adversarially robust optimization with gaussian processes I Bogunovic, J Scarlett, S Jegelka, V Cevher Advances in neural information processing systems 31, 5760-5770, 2018 | 100 | 2018 |
Keyulu XuMITVerified email at mit.edu
