| Co-teaching: Robust training of deep neural networks with extremely noisy labels B Han, Q Yao, X Yu, G Niu, M Xu, W Hu, I Tsang, M Sugiyama Advances in neural information processing systems 31, 2018 | 1434 | 2018 |
| Speedup matrix completion with side information: Application to multi-label learning M Xu, R Jin, ZH Zhou Advances in neural information processing systems 26, 2013 | 286 | 2013 |
| Progressive identification of true labels for partial-label learning J Lv, M Xu, L Feng, G Niu, X Geng, M Sugiyama international conference on machine learning, 6500-6510, 2020 | 98 | 2020 |
| Sigua: Forgetting may make learning with noisy labels more robust B Han, G Niu, X Yu, Q Yao, M Xu, I Tsang, M Sugiyama International Conference on Machine Learning, 4006-4016, 2020 | 87 | 2020 |
| Provably consistent partial-label learning L Feng, J Lv, B Han, M Xu, G Niu, X Geng, B An, M Sugiyama Advances in neural information processing systems 33, 10948-10960, 2020 | 73 | 2020 |
| Active feature acquisition with supervised matrix completion SJ Huang, M Xu, MK Xie, M Sugiyama, G Niu, S Chen Proceedings of the 24th ACM SIGKDD International Conference on Knowledge …, 2018 | 44 | 2018 |
| Incomplete Label Distribution Learning. M Xu, ZH Zhou IJCAI, 3175-3181, 2017 | 37 | 2017 |
| Multi-label learning with PRO loss M Xu, YF Li, ZH Zhou Proceedings of the AAAI Conference on Artificial Intelligence 27 (1), 998-1004, 2013 | 34 | 2013 |
| CUR algorithm for partially observed matrices M Xu, R Jin, ZH Zhou International Conference on Machine Learning, 1412-1421, 2015 | 33 | 2015 |
| Positive-Unlabeled Learning from Imbalanced Data. G Su, W Chen, M Xu IJCAI, 2995-3001, 2021 | 25 | 2021 |
| Robust multi-label learning with PRO loss M Xu, YF Li, ZH Zhou IEEE Transactions on Knowledge and Data Engineering 32 (8), 1610-1624, 2019 | 20 | 2019 |
| Learning from group supervision: the impact of supervision deficiency on multi-label learning M Xu, LZ Guo Science China Information Sciences 64, 1-13, 2021 | 19 | 2021 |
| Pumpout: A meta approach for robustly training deep neural networks with noisy labels B Han, G Niu, J Yao, X Yu, M Xu, I Tsang, M Sugiyama | 18 | 2018 |
| Matrix co-completion for multi-label classification with missing features and labels M Xu, G Niu, B Han, IW Tsang, ZH Zhou, M Sugiyama arXiv preprint arXiv:1805.09156, 2018 | 16 | 2018 |
| Self-Supervised Adversarial Distribution Regularization for Medication Recommendation. Y Wang, W Chen, D Pi, L Yue, S Wang, M Xu IJCAI, 3134-3140, 2021 | 13 | 2021 |
| Co-sampling: Training robust networks for extremely noisy supervision B Han, Q Yao, X Yu, G Niu, M Xu, W Hu, IW Tsang, M Sugiyama arXiv preprint arXiv:1804.06872, 2018 | 11 | 2018 |
| Revisiting sample selection approach to positive-unlabeled learning: Turning unlabeled data into positive rather than negative M Xu, B Li, G Niu, B Han, M Sugiyama arXiv preprint arXiv:1901.10155, 2019 | 10 | 2019 |
| A pseudo-label method for coarse-to-fine multi-label learning with limited supervision CY Hsieh, M Xu, G Niu, HT Lin, M Sugiyama | 10 | 2019 |
| On the robustness of average losses for partial-label learning J Lv, B Liu, L Feng, N Xu, M Xu, B An, G Niu, X Geng, M Sugiyama IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 | 9 | 2023 |
| Pointwise binary classification with pairwise confidence comparisons L Feng, S Shu, N Lu, B Han, M Xu, G Niu, B An, M Sugiyama International Conference on Machine Learning, 3252-3262, 2021 | 9 | 2021 |
Masashi SugiyamaDirector, RIKEN Center for Advanced Intelligence Project / Professor, The University of TokyoVerified email at k.u-tokyo.ac.jp
