Stop the war!Остановите войну!
for scientists:
Google
Google Scholar
Semantic Scholar
IA Scholar
CiteSeerX
ORCIDGang Niu 0001
Person information
- affiliation: RIKEN, Japan
- affiliation (former, PhD 2013): Tokyo Institute of Technology, Department of Computer Science, Japan
- affiliation (former): Nanjing University, State Key Laboratory for Novel Software Technology, Nanjing, China
Other persons with the same name
- Gang Niu 0002 — City University of Hong Kong, Center for Prognostics and System Health Management, Hong Kong (and 1 more)
- Gang Niu 0003 — First Affiliated Hospital of Xi'an Jiaotong University, Department of Radiology, Xi'an, China
- Gang Niu 0004
![[0000-0002-6912-8980]](https://dblp.org/img/orcid-mark.12x12.png "0000-0002-6912-8980")
— Tongji University, Institute of Rail Transit, Shanghai, China - Gang Niu 0005 — Zhengzhou Huali Information Technology Co., Ltd., China
- Gang Niu 0006 — Xi'an Jiaotong University, International Center for Dielectric Research, China
- Gang Niu 0007 — Sun Yat-sen University, First Affiliated Hospital, Department of Obstetrics and Gynecology, Guangzhou, China
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2022
[j15]Yuangang Pan, Ivor W. Tsang, Weijie Chen, Gang Niu, Masashi Sugiyama:
Fast and Robust Rank Aggregation against Model Misspecification. J. Mach. Learn. Res. 23: 23:1-23:35 (2022)- [i80]Haobo Wang, Ruixuan Xiao, Yixuan Li, Lei Feng, Gang Niu, Gang Chen, Junbo Zhao:
PiCO: Contrastive Label Disambiguation for Partial Label Learning. CoRR abs/2201.08984 (2022) - [i79]Takashi Ishida, Ikko Yamane, Nontawat Charoenphakdee, Gang Niu, Masashi Sugiyama:
Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification. CoRR abs/2202.00395 (2022) - [i78]Yinghua Gao, Dongxian Wu, Jingfeng Zhang, Guanhao Gan, Shu-Tao Xia, Gang Niu, Masashi Sugiyama:
On the Effectiveness of Adversarial Training against Backdoor Attacks. CoRR abs/2202.10627 (2022) - [i77]Nan Lu, Zhao Wang, Xiaoxiao Li, Gang Niu, Qi Dou, Masashi Sugiyama:
Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients. CoRR abs/2204.03304 (2022) - [i76]De Cheng, Tongliang Liu, Yixiong Ning, Nannan Wang, Bo Han, Gang Niu, Xinbo Gao, Masashi Sugiyama:
Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation. CoRR abs/2206.02791 (2022) - [i75]Ruize Gao, Jiongxiao Wang, Kaiwen Zhou, Feng Liu, Binghui Xie, Gang Niu, Bo Han, James Cheng:
Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack. CoRR abs/2206.07314 (2022) - 2021
- [j14]Tomoya Sakai, Gang Niu, Masashi Sugiyama:
Information-Theoretic Representation Learning for Positive-Unlabeled Classification. Neural Comput. 33(1): 244-268 (2021) - [j13]Wenkai Xu, Gang Niu, Aapo Hyvärinen, Masashi Sugiyama:
Direction Matters: On Influence-Preserving Graph Summarization and Max-Cut Principle for Directed Graphs. Neural Comput. 33(8): 2128-2162 (2021) - [c64]Qizhou Wang, Bo Han, Tongliang Liu, Gang Niu, Jian Yang, Chen Gong:
Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model. AAAI 2021: 10183-10191 - [c63]Alon Jacovi, Gang Niu, Yoav Goldberg, Masashi Sugiyama:
Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning. EACL 2021: 581-592 - [c62]Jingfeng Zhang, Jianing Zhu, Gang Niu, Bo Han, Masashi Sugiyama, Mohan S. Kankanhalli:
Geometry-aware Instance-reweighted Adversarial Training. ICLR 2021 - [c61]Antonin Berthon, Bo Han, Gang Niu, Tongliang Liu, Masashi Sugiyama:
Confidence Scores Make Instance-dependent Label-noise Learning Possible. ICML 2021: 825-836 - [c60]Yuzhou Cao, Lei Feng, Yitian Xu, Bo An, Gang Niu, Masashi Sugiyama:
Learning from Similarity-Confidence Data. ICML 2021: 1272-1282 - [c59]Shuo Chen, Gang Niu, Chen Gong, Jun Li, Jian Yang, Masashi Sugiyama:
Large-Margin Contrastive Learning with Distance Polarization Regularizer. ICML 2021: 1673-1683 - [c58]Xuefeng Du, Jingfeng Zhang, Bo Han, Tongliang Liu, Yu Rong, Gang Niu, Junzhou Huang, Masashi Sugiyama:
Learning Diverse-Structured Networks for Adversarial Robustness. ICML 2021: 2880-2891 - [c57]Lei Feng, Senlin Shu, Nan Lu, Bo Han, Miao Xu, Gang Niu, Bo An, Masashi Sugiyama:
Pointwise Binary Classification with Pairwise Confidence Comparisons. ICML 2021: 3252-3262 - [c56]Ruize Gao, Feng Liu, Jingfeng Zhang, Bo Han, Tongliang Liu, Gang Niu, Masashi Sugiyama:
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks. ICML 2021: 3564-3575 - [c55]Xuefeng Li, Tongliang Liu, Bo Han, Gang Niu, Masashi Sugiyama:
Provably End-to-end Label-noise Learning without Anchor Points. ICML 2021: 6403-6413 - [c54]Nan Lu, Shida Lei, Gang Niu, Issei Sato, Masashi Sugiyama:
Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification. ICML 2021: 7134-7144 - [c53]Songhua Wu, Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Nannan Wang, Haifeng Liu, Gang Niu:
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels. ICML 2021: 11285-11295 - [c52]Hanshu Yan, Jingfeng Zhang, Gang Niu, Jiashi Feng, Vincent Y. F. Tan, Masashi Sugiyama:
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection. ICML 2021: 11693-11703 - [c51]Yivan Zhang, Gang Niu, Masashi Sugiyama:
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization. ICML 2021: 12501-12512 - [c50]Lei Feng, Senlin Shu, Yuzhou Cao, Lue Tao, Hongxin Wei, Tao Xiang, Bo An, Gang Niu:
Multiple-Instance Learning from Similar and Dissimilar Bags. KDD 2021: 374-382 - [c49]Yu Yao, Tongliang Liu, Mingming Gong, Bo Han, Gang Niu, Kun Zhang:
Instance-dependent Label-noise Learning under a Structural Causal Model. NeurIPS 2021: 4409-4420 - [c48]Qizhou Wang, Feng Liu, Bo Han, Tongliang Liu, Chen Gong, Gang Niu, Mingyuan Zhou, Masashi Sugiyama:
Probabilistic Margins for Instance Reweighting in Adversarial Training. NeurIPS 2021: 23258-23269 - [c47]Yingbin Bai, Erkun Yang, Bo Han, Yanhua Yang, Jiatong Li, Yinian Mao, Gang Niu, Tongliang Liu:
Understanding and Improving Early Stopping for Learning with Noisy Labels. NeurIPS 2021: 24392-24403 - [i74]Qizhou Wang, Bo Han, Tongliang Liu, Gang Niu, Jian Yang, Chen Gong:
Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model. CoRR abs/2101.05467 (2021) - [i73]Shida Lei, Nan Lu, Gang Niu, Issei Sato, Masashi Sugiyama:
Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification. CoRR abs/2102.00678 (2021) - [i72]Xuefeng Du, Jingfeng Zhang, Bo Han, Tongliang Liu, Yu Rong, Gang Niu, Junzhou Huang, Masashi Sugiyama:
Learning Diverse-Structured Networks for Adversarial Robustness. CoRR abs/2102.01886 (2021) - [i71]Xuefeng Li, Tongliang Liu, Bo Han, Gang Niu, Masashi Sugiyama:
Provably End-to-end Label-Noise Learning without Anchor Points. CoRR abs/2102.02400 (2021) - [i70]Yivan Zhang, Gang Niu, Masashi Sugiyama:
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization. CoRR abs/2102.02414 (2021) - [i69]Jianing Zhu, Jingfeng Zhang, Bo Han, Tongliang Liu, Gang Niu, Hongxia Yang, Mohan S. Kankanhalli, Masashi Sugiyama:
Understanding the Interaction of Adversarial Training with Noisy Labels. CoRR abs/2102.03482 (2021) - [i68]Haoang Chi, Feng Liu, Wenjing Yang, Long Lan, Tongliang Liu, Gang Niu, Bo Han:
Meta Discovery: Learning to Discover Novel Classes given Very Limited Data. CoRR abs/2102.04002 (2021) - [i67]Hanshu Yan, Jingfeng Zhang, Gang Niu, Jiashi Feng, Vincent Y. F. Tan, Masashi Sugiyama:
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection. CoRR abs/2102.05311 (2021) - [i66]Yuzhou Cao, Lei Feng, Yitian Xu, Bo An, Gang Niu, Masashi Sugiyama:
Learning from Similarity-Confidence Data. CoRR abs/2102.06879 (2021) - [i65]Chen Chen, Jingfeng Zhang, Xilie Xu, Tianlei Hu, Gang Niu, Gang Chen, Masashi Sugiyama:
Guided Interpolation for Adversarial Training. CoRR abs/2102.07327 (2021) - [i64]Shuo Yang, Erkun Yang, Bo Han, Yang Liu, Min Xu, Gang Niu, Tongliang Liu:
Estimating Instance-dependent Label-noise Transition Matrix using DNNs. CoRR abs/2105.13001 (2021) - [i63]Jingfeng Zhang, Xilie Xu, Bo Han, Tongliang Liu, Gang Niu, Lizhen Cui, Masashi Sugiyama:
NoiLIn: Do Noisy Labels Always Hurt Adversarial Training? CoRR abs/2105.14676 (2021) - [i62]Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu, Gang Niu, Masashi Sugiyama:
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels. CoRR abs/2106.00445 (2021) - [i61]Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu, Gang Niu, Masashi Sugiyama:
Instance Correction for Learning with Open-set Noisy Labels. CoRR abs/2106.00455 (2021) - [i60]Jiaheng Wei, Hangyu Liu, Tongliang Liu, Gang Niu, Yang Liu:
Understanding (Generalized) Label Smoothing when Learning with Noisy Labels. CoRR abs/2106.04149 (2021) - [i59]Jianing Zhu, Jiangchao Yao, Bo Han, Jingfeng Zhang, Tongliang Liu, Gang Niu, Jingren Zhou, Jianliang Xu, Hongxia Yang:
Reliable Adversarial Distillation with Unreliable Teachers. CoRR abs/2106.04928 (2021) - [i58]Jiaqi Lv, Lei Feng, Miao Xu, Bo An, Gang Niu, Xin Geng, Masashi Sugiyama:
On the Robustness of Average Losses for Partial-Label Learning. CoRR abs/2106.06152 (2021) - [i57]Yonggang Zhang, Mingming Gong, Tongliang Liu, Gang Niu, Xinmei Tian, Bo Han, Bernhard Schölkopf, Kun Zhang:
Adversarial Robustness through the Lens of Causality. CoRR abs/2106.06196 (2021) - [i56]Qizhou Wang, Feng Liu, Bo Han, Tongliang Liu, Chen Gong, Gang Niu, Mingyuan Zhou, Masashi Sugiyama:
Probabilistic Margins for Instance Reweighting in Adversarial Training. CoRR abs/2106.07904 (2021) - [i55]Yuzhou Cao, Lei Feng, Senlin Shu, Yitian Xu, Bo An, Gang Niu, Masashi Sugiyama:
Multi-Class Classification from Single-Class Data with Confidences. CoRR abs/2106.08864 (2021) - [i54]Ruize Gao, Feng Liu, Kaiwen Zhou, Gang Niu, Bo Han, James Cheng:
Local Reweighting for Adversarial Training. CoRR abs/2106.15776 (2021) - [i53]Yingbin Bai, Erkun Yang, Bo Han, Yanhua Yang, Jiatong Li, Yinian Mao, Gang Niu, Tongliang Liu:
Understanding and Improving Early Stopping for Learning with Noisy Labels. CoRR abs/2106.15853 (2021) - [i52]Yu Yao, Tongliang Liu, Mingming Gong, Bo Han, Gang Niu, Kun Zhang:
Instance-dependent Label-noise Learning under a Structural Causal Model. CoRR abs/2109.02986 (2021) - [i51]Cheng-Yu Hsieh, Wei-I Lin, Miao Xu, Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama:
Active Refinement for Multi-Label Learning: A Pseudo-Label Approach. CoRR abs/2109.14676 (2021) - [i50]Jiaheng Wei, Zhaowei Zhu, Hao Cheng, Tongliang Liu, Gang Niu, Yang Liu:
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations. CoRR abs/2110.12088 (2021) - 2020
- [c46]Chao Li, Mohammad Emtiyaz Khan, Zhun Sun, Gang Niu, Bo Han, Shengli Xie, Qibin Zhao:
Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition Under Reshuffling. AAAI 2020: 4602-4609 - [c45]Nan Lu, Tianyi Zhang, Gang Niu, Masashi Sugiyama:
Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach. AISTATS 2020: 1115-1125 - [c44]Chun Wang, Bo Han, Shirui Pan, Jing Jiang, Gang Niu, Guodong Long:
Cross-Graph: Robust and Unsupervised Embedding for Attributed Graphs with Corrupted Structure. ICDM 2020: 571-580 - [c43]Yu-Ting Chou, Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama:
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels. ICML 2020: 1929-1938 - [c42]Lei Feng, Takuo Kaneko, Bo Han, Gang Niu, Bo An, Masashi Sugiyama:
Learning with Multiple Complementary Labels. ICML 2020: 3072-3081 - [c41]Bo Han, Gang Niu, Xingrui Yu, Quanming Yao, Miao Xu, Ivor W. Tsang, Masashi Sugiyama:
SIGUA: Forgetting May Make Learning with Noisy Labels More Robust. ICML 2020: 4006-4016 - [c40]Takashi Ishida, Ikko Yamane, Tomoya Sakai, Gang Niu, Masashi Sugiyama:
Do We Need Zero Training Loss After Achieving Zero Training Error? ICML 2020: 4604-4614 - [c39]Jiaqi Lv, Miao Xu, Lei Feng, Gang Niu, Xin Geng, Masashi Sugiyama:
Progressive Identification of True Labels for Partial-Label Learning. ICML 2020: 6500-6510 - [c38]Quanming Yao, Hansi Yang, Bo Han, Gang Niu, James Tin-Yau Kwok:
Searching to Exploit Memorization Effect in Learning with Noisy Labels. ICML 2020: 10789-10798 - [c37]Jingfeng Zhang, Xilie Xu, Bo Han, Gang Niu, Lizhen Cui, Masashi Sugiyama, Mohan S. Kankanhalli:
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger. ICML 2020: 11278-11287 - [c36]Tongtong Fang, Nan Lu, Gang Niu, Masashi Sugiyama:
Rethinking Importance Weighting for Deep Learning under Distribution Shift. NeurIPS 2020 - [c35]Lei Feng, Jiaqi Lv, Bo Han, Miao Xu, Gang Niu, Xin Geng, Bo An, Masashi Sugiyama:
Provably Consistent Partial-Label Learning. NeurIPS 2020 - [c34]Xiaobo Xia, Tongliang Liu, Bo Han, Nannan Wang, Mingming Gong, Haifeng Liu, Gang Niu, Dacheng Tao, Masashi Sugiyama:
Part-dependent Label Noise: Towards Instance-dependent Label Noise. NeurIPS 2020 - [c33]Yu Yao, Tongliang Liu, Bo Han, Mingming Gong, Jiankang Deng, Gang Niu, Masashi Sugiyama:
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning. NeurIPS 2020 - [i49]Antonin Berthon, Bo Han, Gang Niu, Tongliang Liu, Masashi Sugiyama:
Confidence Scores Make Instance-dependent Label-noise Learning Possible. CoRR abs/2001.03772 (2020) - [i48]Yu Yao, Tongliang Liu, Bo Han, Mingming Gong, Gang Niu, Masashi Sugiyama, Dacheng Tao:
Towards Mixture Proportion Estimation without Irreducibility. CoRR abs/2002.03673 (2020) - [i47]Songhua Wu, Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Nannan Wang, Haifeng Liu, Gang Niu:
Multi-Class Classification from Noisy-Similarity-Labeled Data. CoRR abs/2002.06508 (2020) - [i46]Jiaqi Lv, Miao Xu, Lei Feng, Gang Niu, Xin Geng, Masashi Sugiyama:
Progressive Identification of True Labels for Partial-Label Learning. CoRR abs/2002.08053 (2020) - [i45]Takashi Ishida, Ikko Yamane, Tomoya Sakai, Gang Niu, Masashi Sugiyama:
Do We Need Zero Training Loss After Achieving Zero Training Error? CoRR abs/2002.08709 (2020) - [i44]Jingfeng Zhang, Xilie Xu, Bo Han, Gang Niu, Lizhen Cui, Masashi Sugiyama, Mohan S. Kankanhalli:
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger. CoRR abs/2002.11242 (2020) - [i43]Tongtong Fang, Nan Lu, Gang Niu, Masashi Sugiyama:
Rethinking Importance Weighting for Deep Learning under Distribution Shift. CoRR abs/2006.04662 (2020) - [i42]Yu Yao, Tongliang Liu, Bo Han, Mingming Gong, Jiankang Deng, Gang Niu, Masashi Sugiyama:
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning. CoRR abs/2006.07805 (2020) - [i41]Songhua Wu, Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Nannan Wang, Haifeng Liu, Gang Niu:
Class2Simi: A New Perspective on Learning with Label Noise. CoRR abs/2006.07831 (2020) - [i40]Xiaobo Xia, Tongliang Liu, Bo Han, Nannan Wang, Mingming Gong, Haifeng Liu, Gang Niu, Dacheng Tao, Masashi Sugiyama:
Parts-dependent Label Noise: Towards Instance-dependent Label Noise. CoRR abs/2006.07836 (2020) - [i39]Yu-Ting Chou, Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama:
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels. CoRR abs/2007.02235 (2020) - [i38]Lei Feng, Jiaqi Lv, Bo Han, Miao Xu, Gang Niu, Xin Geng, Bo An, Masashi Sugiyama:
Provably Consistent Partial-Label Learning. CoRR abs/2007.08929 (2020) - [i37]Jingfeng Zhang, Jianing Zhu, Gang Niu, Bo Han, Masashi Sugiyama, Mohan S. Kankanhalli:
Geometry-aware Instance-reweighted Adversarial Training. CoRR abs/2010.01736 (2020) - [i36]Lei Feng, Senlin Shu, Nan Lu, Bo Han, Miao Xu, Gang Niu, Bo An, Masashi Sugiyama:
Pointwise Binary Classification with Pairwise Confidence Comparisons. CoRR abs/2010.01875 (2020) - [i35]Ruize Gao, Feng Liu, Jingfeng Zhang, Bo Han, Tongliang Liu, Gang Niu, Masashi Sugiyama:
Maximum Mean Discrepancy is Aware of Adversarial Attacks. CoRR abs/2010.11415 (2020) - [i34]Bo Han, Quanming Yao, Tongliang Liu, Gang Niu, Ivor W. Tsang, James T. Kwok, Masashi Sugiyama:
A Survey of Label-noise Representation Learning: Past, Present and Future. CoRR abs/2011.04406 (2020) - [i33]Zhuowei Wang, Jing Jiang, Bo Han, Lei Feng, Bo An, Gang Niu, Guodong Long:
SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning. CoRR abs/2012.00925 (2020)
2010 – 2019
- 2019
- [c32]Nan Lu, Gang Niu, Aditya Krishna Menon, Masashi Sugiyama:
On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data. ICLR (Poster) 2019 - [c31]Yu-Guan Hsieh, Gang Niu, Masashi Sugiyama:
Classification from Positive, Unlabeled and Biased Negative Data. ICML 2019: 2820-2829 - [c30]Takashi Ishida, Gang Niu, Aditya Krishna Menon, Masashi Sugiyama:
Complementary-Label Learning for Arbitrary Losses and Models. ICML 2019: 2971-2980 - [c29]Xingrui Yu, Bo Han, Jiangchao Yao, Gang Niu, Ivor W. Tsang, Masashi Sugiyama:
How does Disagreement Help Generalization against Label Corruption? ICML 2019: 7164-7173 - [c28]Liyuan Xu, Junya Honda, Gang Niu, Masashi Sugiyama:
Uncoupled Regression from Pairwise Comparison Data. NeurIPS 2019: 3994-4004 - [c27]Xiaobo Xia, Tongliang Liu, Nannan Wang, Bo Han, Chen Gong, Gang Niu, Masashi Sugiyama:
Are Anchor Points Really Indispensable in Label-Noise Learning? NeurIPS 2019: 6835-6846 - [i32]Xingrui Yu, Bo Han, Jiangchao Yao, Gang Niu, Ivor W. Tsang, Masashi Sugiyama:
How does Disagreement Help Generalization against Label Corruption? CoRR abs/1901.04215 (2019) - [i31]Miao Xu, Bingcong Li, Gang Niu, Bo Han, Masashi Sugiyama:
Revisiting Sample Selection Approach to Positive-Unlabeled Learning: Turning Unlabeled Data into Positive rather than Negative. CoRR abs/1901.10155 (2019) - [i30]Feng Liu, Jie Lu, Bo Han, Gang Niu, Guangquan Zhang, Masashi Sugiyama:
Butterfly: A Panacea for All Difficulties in Wildly Unsupervised Domain Adaptation. CoRR abs/1905.07720 (2019) - [i29]Yuangang Pan, Weijie Chen, Gang Niu, Ivor W. Tsang, Masashi Sugiyama:
Fast and Robust Rank Aggregation against Model Misspecification. CoRR abs/1905.12341 (2019) - [i28]Liyuan Xu, Junya Honda, Gang Niu, Masashi Sugiyama:
Uncoupled Regression from Pairwise Comparison Data. CoRR abs/1905.13659 (2019) - [i27]Xiaobo Xia, Tongliang Liu, Nannan Wang, Bo Han, Chen Gong, Gang Niu, Masashi Sugiyama:
Are Anchor Points Really Indispensable in Label-Noise Learning? CoRR abs/1906.00189 (2019) - [i26]Wenkai Xu, Gang Niu, Aapo Hyvärinen, Masashi Sugiyama:
Direction Matters: On Influence-Preserving Graph Summarization and Max-cut Principle for Directed Graphs. CoRR abs/1907.09588 (2019) - [i25]Nan Lu, Tianyi Zhang, Gang Niu, Masashi Sugiyama:
Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach. CoRR abs/1910.08974 (2019) - [i24]Alon Jacovi, Gang Niu, Yoav Goldberg, Masashi Sugiyama:
Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning. CoRR abs/1910.13339 (2019) - [i23]Hansi Yang, Quanming Yao, Bo Han, Gang Niu:
Searching to Exploit Memorization Effect in Learning from Corrupted Labels. CoRR abs/1911.02377 (2019) - [i22]Jingfeng Zhang, Bo Han, Gang Niu, Tongliang Liu, Masashi Sugiyama:
Where is the Bottleneck of Adversarial Learning with Unlabeled Data? CoRR abs/1911.08696 (2019) - 2018
- [j12]Tomoya Sakai, Gang Niu, Masashi Sugiyama:
Semi-supervised AUC optimization based on positive-unlabeled learning. Mach. Learn. 107(4): 767-794 (2018) - [j11]Tomoya Sakai, Gang Niu, Masashi Sugiyama:
Correction to: Semi-supervised AUC optimization based on positive-unlabeled learning. Mach. Learn. 107(4): 795 (2018) - [j10]Hiroaki Sasaki, Voot Tangkaratt, Gang Niu, Masashi Sugiyama:
Sufficient Dimension Reduction via Direct Estimation of the Gradients of Logarithmic Conditional Densities. Neural Comput. 30(2) (2018) - [c26]Han Bao, Gang Niu, Masashi Sugiyama:
Classification from Pairwise Similarity and Unlabeled Data. ICML 2018: 461-470 - [c25]Weihua Hu, Gang Niu, Issei Sato, Masashi Sugiyama:
Does Distributionally Robust Supervised Learning Give Robust Classifiers? ICML 2018: 2034-2042 - [c24]Sheng-Jun Huang, Miao Xu, Ming-Kun Xie, Masashi Sugiyama, Gang Niu, Songcan Chen:
Active Feature Acquisition with Supervised Matrix Completion. KDD 2018: 1571-1579 - [c23]Bo Han, Jiangchao Yao, Gang Niu, Mingyuan Zhou, Ivor W. Tsang, Ya Zhang, Masashi Sugiyama:
Masking: A New Perspective of Noisy Supervision. NeurIPS 2018: 5841-5851 - [c22]Takashi Ishida, Gang Niu, Masashi Sugiyama:
Binary Classification from Positive-Confidence Data. NeurIPS 2018: 5921-5932 - [c21]Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor W. Tsang, Masashi Sugiyama:
Co-teaching: Robust training of deep neural networks with extremely noisy labels. NeurIPS 2018: 8536-8546 - [i21]Han Bao, Gang Niu, Masashi Sugiyama:
Classification from Pairwise Similarity and Unlabeled Data. CoRR abs/1802.04381 (2018) - [i20]Sheng-Jun Huang, Miao Xu, Ming-Kun Xie, Masashi Sugiyama, Gang Niu, Songcan Chen:
Active Feature Acquisition with Supervised Matrix Completion. CoRR abs/1802.05380 (2018) - [i19]Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor W. Tsang, Masashi Sugiyama:
Co-sampling: Training Robust Networks for Extremely Noisy Supervision. CoRR abs/1804.06872 (2018) - [i18]Bo Han, Jiangchao Yao, Gang Niu, Mingyuan Zhou, Ivor W. Tsang, Ya Zhang, Masashi Sugiyama:
Masking: A New Perspective of Noisy Supervision. CoRR abs/1805.08193 (2018) - [i17]Miao Xu, Gang Niu, Bo Han, Ivor W. Tsang, Zhi-Hua Zhou, Masashi Sugiyama:
Matrix Co-completion for Multi-label Classification with Missing Features and Labels. CoRR abs/1805.09156 (2018) - [i16]Nan Lu, Gang Niu, Aditya Krishna Menon, Masashi Sugiyama:
On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data. CoRR abs/1808.10585 (2018) - [i15]Masahiro Kato, Liyuan Xu, Gang Niu, Masashi Sugiyama:
Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data. CoRR abs/1809.05710 (2018) - [i14]Bo Han, Gang Niu, Jiangchao Yao, Xingrui Yu, Miao Xu, Ivor W. Tsang, Masashi Sugiyama:
Pumpout: A Meta Approach for Robustly Training Deep Neural Networks with Noisy Labels. CoRR abs/1809.11008 (2018) - [i13]Yu-Guan Hsieh, Gang Niu, Masashi Sugiyama:
Classification from Positive, Unlabeled and Biased Negative Data. CoRR abs/1810.00846 (2018) - [i12]Takashi Ishida, Gang Niu, Aditya Krishna Menon, Masashi Sugiyama:
Complementary-Label Learning for Arbitrary Losses and Models. CoRR abs/1810.04327 (2018) - 2017
- [j9]Hiroaki Sasaki, Takafumi Kanamori, Aapo Hyvärinen, Gang Niu, Masashi Sugiyama:
Mode-Seeking Clustering and Density Ridge Estimation via Direct Estimation of Density-Derivative-Ratios. J. Mach. Learn. Res. 18: 180:1-180:47 (2017) - [j8]Marthinus Christoffel du Plessis, Gang Niu, Masashi Sugiyama:
Class-prior estimation for learning from positive and unlabeled data. Mach. Learn. 106(4): 463-492 (2017) - [c20]Hiroaki Shiino, Hiroaki Sasaki, Gang Niu, Masashi Sugiyama:
Whitening-Free Least-Squares Non-Gaussian Component Analysis. ACML 2017: 375-390 - [c19]Tomoya Sakai, Marthinus Christoffel du Plessis, Gang Niu, Masashi Sugiyama:
Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data. ICML 2017: 2998-3006 - [c18]Ryuichi Kiryo, Gang Niu, Marthinus Christoffel du Plessis, Masashi Sugiyama:
Positive-Unlabeled Learning with Non-Negative Risk Estimator. NIPS 2017: 1675-1685 - [c17]Takashi Ishida, Gang Niu, Weihua Hu, Masashi Sugiyama:
Learning from Complementary Labels. NIPS 2017: 5639-5649 - [i11]