Miao Xu
Miao Xu
RIKEN, AIP
Verified email at lamda.nju.edu.cn - Homepage
Title
Cited by
Cited by
Year
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
arXiv preprint arXiv:1804.06872, 2018
5742018
Speedup matrix completion with side information: Application to multi-label learning
M Xu, R Jin, ZH Zhou
Advances in neural information processing systems, 2301-2309, 2013
2262013
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
362020
Multi-label learning with PRO loss
M Xu, YF Li, ZH Zhou
Proceedings of the AAAI Conference on Artificial Intelligence 27 (1), 2013
352013
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
262018
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
252020
CUR algorithm for partially observed matrices
M Xu, R Jin, ZH Zhou
International Conference on Machine Learning, 1412-1421, 2015
232015
Incomplete Label Distribution Learning.
M Xu, ZH Zhou
IJCAI, 3175-3181, 2017
172017
Provably consistent partial-label learning
L Feng, J Lv, B Han, M Xu, G Niu, X Geng, B An, M Sugiyama
arXiv preprint arXiv:2007.08929, 2020
152020
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
112018
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
102019
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
72018
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
72018
Learning from group supervision: the impact of supervision deficiency on multi-label learning
M Xu, LZ Guo
Science China Information Sciences 64 (3), 1-13, 2021
52021
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
42019
Basic research on flow of nanofluids in cooling system of internal combustion engine
WZ Cui, ML Bai, JZ Lv, L Zhang, XJ Li, M Xu
Transactions of Chinese Society for Internal Combustion Engines 30 (1), 49-55, 2012
42012
Clipped matrix completion: A remedy for ceiling effects
T Teshima, M Xu, I Sato, M Sugiyama
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 5151-5158, 2019
32019
Pumpout: A meta approach to robust deep learning with noisy labels
B Han, G Niu, J Yao, X Yu, M Xu, I Tsang, M Sugiyama
arXiv preprint arXiv:1809.11008, 2018
32018
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
22021
A Pseudo-Label Method for Coarse-to-Fine Multi-Label Learning with Limited Supervision
CY Hsieh, M Xu, G Niu, HT Lin, M Sugiyama
22019
The system can't perform the operation now. Try again later.
Articles 1–20