| Towards robust interpretability with self-explaining neural networks D Alvarez-Melis, TS Jaakkola Advances in Neural Information Processing Systems, 7775-7784, 2018 | 1129 | 2018 |
| On the robustness of interpretability methods D Alvarez-Melis, TS Jaakkola Proceedings of the 2018 ICML Workshop on Human Interpretability in Machine …, 2018 | 729 | 2018 |
| Gromov-Wasserstein alignment of word embedding spaces D Alvarez-Melis, TS Jaakkola Proceedings of the 2018 Conference on Empirical Methods in Natural Language …, 2018 | 351 | 2018 |
| A causal framework for explaining the predictions of black-box sequence-to-sequence models D Alvarez-Melis, TS Jaakkola Proceedings of the 2017 Conference on Empirical Methods in Natural Language …, 2017 | 270 | 2017 |
| Geometric Dataset Distances via Optimal Transport D Alvarez-Melis, N Fusi Advances in Neural Information Processing Systems 33, 21428--21439, 2020 | 209 | 2020 |
| Topic Modeling in Twitter: Aggregating Tweets by Conversations. D Alvarez-Melis, M Saveski Proceedings of the Tenth International Conference on Web and Social Media …, 2016 | 186 | 2016 |
| Learning generative models across incomparable spaces C Bunne, D Alvarez-Melis, A Krause, S Jegelka International conference on machine learning, 851-861, 2019 | 123 | 2019 |
| Tree-structured decoding with doubly-recurrent neural networks D Alvarez-Melis, TS Jaakkola International Conference on Learning Representations (ICLR), 2017 | 109 | 2017 |
| Word embeddings as metric recovery in semantic spaces TB Hashimoto, D Alvarez-Melis, TS Jaakkola Transactions of the Association for Computational Linguistics 4, 273-286, 2016 | 103 | 2016 |
| Towards Optimal Transport with Global Invariances D Alvarez-Melis, S Jegelka, TS Jaakkola International Conference on Artificial Intelligence and Statistics (AISTATS), 2019 | 80 | 2019 |
| Structured Optimal Transport D Alvarez-Melis, TS Jaakkola, S Jegelka International Conference on Artificial Intelligence and Statistics (AISTATS …, 2018 | 70 | 2018 |
| Optimizing functionals on the space of probabilities with input convex neural networks D Alvarez-Melis, Y Schiff, Y Mroueh arXiv preprint arXiv:2106.00774, 2021 | 56 | 2021 |
| Distributional adversarial networks C Li, D Alvarez-Melis, K Xu, S Jegelka, S Sra arXiv preprint arXiv:1706.09549, 2017 | 49* | 2017 |
| Towards robust, locally linear deep networks GH Lee, D Alvarez-Melis, TS Jaakkola International Conference on Learning Representations, 2019 | 48 | 2019 |
| From human explanation to model interpretability: A framework based on weight of evidence DA Melis, H Kaur, H Daumé III, H Wallach, JW Vaughan Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 9 …, 2021 | 30 | 2021 |
| Unsupervised hierarchy matching with optimal transport over hyperbolic spaces D Alvarez-Melis, Y Mroueh, T Jaakkola International Conference on Artificial Intelligence and Statistics, 1606-1617, 2020 | 28 | 2020 |
| Weight of evidence as a basis for human-oriented explanations D Alvarez-Melis, H Daumé III, JW Vaughan, H Wallach arXiv preprint arXiv:1910.13503, 2019 | 25 | 2019 |
| Functional transparency for structured data: a game-theoretic approach GH Lee, W Jin, D Alvarez-Melis, T Jaakkola International Conference on Machine Learning, 3723-3733, 2019 | 23 | 2019 |
| Neural unbalanced optimal transport via cycle-consistent semi-couplings F Lübeck, C Bunne, G Gut, JS del Castillo, L Pelkmans, D Alvarez-Melis arXiv preprint arXiv:2209.15621, 2022 | 20 | 2022 |
| Dataset dynamics via gradient flows in probability space D Alvarez-Melis, N Fusi International conference on machine learning, 219-230, 2021 | 20 | 2021 |
Tommi JaakkolaMITVerified email at csail.mit.edu
