Gang Niu

发表

Convex Formulation for Learning from Positive and Unlabeled Data

Gang Niu, Masashi Sugiyama, Marthinus Christoffel du Plessis, 2015, ICML.

Does Distributionally Robust Supervised Learning Give Robust Classifiers?

Gang Niu, Masashi Sugiyama, Issei Sato, 2016, ICML.

Direct Density Derivative Estimation

Gang Niu, Masashi Sugiyama, Hiroaki Sasaki, 2016, Neural Computation.

Maximum volume clustering: a new discriminative clustering approach

Gang Niu, Bo Dai, Masashi Sugiyama, 2013, J. Mach. Learn. Res..

Suffcient Component Analysis

Masashi Sugiyama, M. Yamada, Gang Niu, 2011, ACML.

Progressive Identification of True Labels for Partial-Label Learning

Masashi Sugiyama, M. Sugiyama, Gang Niu, 2020, ICML.

Attacks Which Do Not Kill Training Make Adversarial Learning Stronger

Mohan S. Kankanhalli, Masashi Sugiyama, Li-zhen Cui, 2020, ICML.

Provably Consistent Partial-Label Learning

Masashi Sugiyama, M. Sugiyama, Bo Han, 2020, Neural Information Processing Systems.

Learning from Multiple Complementary Labels

Masashi Sugiyama, Bo Han, Gang Niu, 2019, arXiv.org.

Co-teaching + : Towards Training of Robust Deep Networks with Noisy Labels

Masashi Sugiyama, I. Tsang, Bo Han, 2019 .

Semi-Supervised Classification based on Positive-Unlabeled Classification

Masashi Sugiyama, M. Plessis, Gang Niu, 2017 .

Maximum Mean Discrepancy is Aware of Adversarial Attacks pdf

Tongliang Liu, Masashi Sugiyama, Bo Han, 2020, ArXiv.

Attacks Which Do Not Kill Training Make Adversarial Learning Stronger

Gang Niu, Masashi Sugiyama, Mohan Kankanhalli, 2020, ICML.

Revisiting Distributionally Robust Supervised Learning in Classification

Masashi Sugiyama, Issei Sato, Weihua Hu, 2016, 1611.02041.

Instance-dependent Label-noise Learning under a Structural Causal Model

Mingming Gong, Tongliang Liu, Bo Han, 2021, NeurIPS.

A Pseudo-Label Method for Coarse-to-Fine Multi-Label Learning with Limited Supervision

Miao Xu, Gang Niu, Masashi Sugiyama, 2019 .

Learning with Multiple Complementary Labels

Masashi Sugiyama, Bo Han, Gang Niu, 2020, Proceedings of the 37th International Conference on Machine Learning.

F EDERATED L EARNING FROM O NLY U NLABELED D ATA WITH C LASS -C ONDITIONAL -S HARING C LIENTS

M. Sugiyama, Gang Niu, Nan Lu, 2022 .

Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach

Masashi Sugiyama, Gang Niu, Tianyi Zhang, 2019, AISTATS.

Information-Maximization Clustering Based on Squared-Loss Mutual Information

Masashi Sugiyama, H. Hachiya, M. Yamada, 2011, Neural Computation.

Meta Discovery: Learning to Discover Novel Classes given Very Limited Data

Tongliang Liu, Bo Han, Gang Niu, 2021, ICLR.

PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning

Yixuan Li, J. Zhao, Gang Niu, 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

On the Robustness of Average Losses for Partial-Label Learning

Masashi Sugiyama, M. Sugiyama, Gang Niu, 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Learning from Noisy Pairwise Similarity and Unlabeled Data

Masashi Sugiyama, Pradeep Ravikumar, M. Sugiyama, 2022, J. Mach. Learn. Res..

To Smooth or Not? When Label Smoothing Meets Noisy Labels

Tongliang Liu, Gang Niu, Jiaheng Wei, 2021, ICML.

Rethinking Importance Weighting for Deep Learning under Distribution Shift

Masashi Sugiyama, M. Sugiyama, Gang Niu, 2020, NeurIPS.

NoiLin: Improving adversarial training and correcting stereotype of noisy labels

Masashi Sugiyama, M. Sugiyama, Tongliang Liu, 2021, Trans. Mach. Learn. Res..

Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization

Gang Niu, Masashi Sugiyama, Yivan Zhang, 2021, ICML.

Transductive Learning with Multi-class Volume Approximation pdf

Gang Niu, Bo Dai, Masashi Sugiyama, 2014, ICML.

Maximum Volume Clustering

Gang Niu, Bo Dai, Masashi Sugiyama, 2011, AISTATS.

Do We Need Zero Training Loss After Achieving Zero Training Error?

Masashi Sugiyama, M. Sugiyama, Gang Niu, 2020, ICML.

Probabilistic Margins for Instance Reweighting in Adversarial Training

Masashi Sugiyama, Mingyuan Zhou, M. Sugiyama, 2021, NeurIPS.

Information-Theoretic Semi-Supervised Metric Learning via Entropy Regularization

Gang Niu, Bo Dai, Masashi Sugiyama, 2012, Neural Computation.

Maximum Mean Discrepancy Test is Aware of Adversarial Attacks

Masashi Sugiyama, Jingfeng Zhang, Tongliang Liu, 2020, ICML.

Parts-dependent Label Noise: Towards Instance-dependent Label Noise pdf

Gang Niu, Nannan Wang, Tongliang Liu, 2020, ArXiv.

SIGUA: Forgetting May Make Learning with Noisy Labels More Robust

Xingrui Yu, Ivor W. Tsang, Gang Niu, 2018, ICML.

Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition Under Reshuffling

M. E. Khan, Bo Han, Qibin Zhao, 2018, AAAI.

Non-Gaussian Component Analysis with Log-Density Gradient Estimation

Gang Niu, Masashi Sugiyama, Hiroaki Sasaki, 2015, AISTATS.

How does Disagreement Help Generalization against Label Corruption?

Xingrui Yu, Ivor W. Tsang, Gang Niu, 2019, ICML.

Co-teaching: Robust training of deep neural networks with extremely noisy labels

Xingrui Yu, Ivor W. Tsang, Gang Niu, 2018, NeurIPS.

Direction Matters: On Influence-Preserving Graph Summarization and Max-Cut Principle for Directed Graphs pdf

Gang Niu, Aapo Hyvärinen, Masashi Sugiyama, 2019, Neural Computation.

Cross-Graph: Robust and Unsupervised Embedding for Attributed Graphs with Corrupted Structure

Guodong Long, Jing Jiang, Shirui Pan, 2020, 2020 IEEE International Conference on Data Mining (ICDM).

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients

Masashi Sugiyama, M. Sugiyama, Gang Niu, 2022, ICLR.

Towards Mixture Proportion Estimation without Irreducibility pdf

Gang Niu, Yu Yao, Masashi Sugiyama, 2020, ArXiv.

Positive-Unlabeled Learning with Non-Negative Risk Estimator pdf

Gang Niu, Masashi Sugiyama, Marthinus Christoffel du Plessis, 2017, NIPS.

Multi-Class Classification from Single-Class Data with Confidences pdf

Gang Niu, Masashi Sugiyama, Senlin Shu, 2021, ArXiv.

Learning from Similarity-Confidence Data

Gang Niu, Masashi Sugiyama, Yuzhou Cao, 2021, ICML.

Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification

Masashi Sugiyama, Issei Sato, M. Sugiyama, 2021, ICML.

On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data pdf

Gang Niu, Masashi Sugiyama, Aditya Krishna Menon, 2018, ICLR.

Binary Classification from Positive-Confidence Data

Gang Niu, Masashi Sugiyama, Takashi Ishida, 2017, NeurIPS.

Learning from Complementary Labels

Gang Niu, Masashi Sugiyama, Takashi Ishida, 2017, NIPS.

Class-prior estimation for learning from positive and unlabeled data

Gang Niu, Masashi Sugiyama, Marthinus Christoffel du Plessis, 2016, Machine Learning.

Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning

Gang Niu, Tomoya Sakai, Masashi Sugiyama, 2016, NIPS.

Theoretical Comparisons of Learning from Positive-Negative, Positive-Unlabeled, and Negative-Unlabeled Data pdf

Gang Niu, Tomoya Sakai, Masashi Sugiyama, 2016, ArXiv.

Squared-loss Mutual Information Regularization: A Novel Information-theoretic Approach to Semi-supervised Learning

Gang Niu, Bo Dai, Masashi Sugiyama, 2013, ICML.

Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification

Masashi Sugiyama, M. Sugiyama, Gang Niu, 2022, ICLR.

Classification from Positive, Unlabeled and Biased Negative Data

Gang Niu, Masashi Sugiyama, Yu-Guan Hsieh, 2018, ICML.

Analysis of Learning from Positive and Unlabeled Data

Gang Niu, Masashi Sugiyama, Marthinus Christoffel du Plessis, 2014, NIPS.

Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data

Gang Niu, Tomoya Sakai, Masashi Sugiyama, 2016, ICML.

Searching to Exploit Memorization Effect in Learning with Noisy Labels

Gang Niu, James T. Kwok, Quanming Yao, 2020, ICML.

Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations

Tongliang Liu, Gang Niu, Jiaheng Wei, 2021, ICLR.

Understanding the Interaction of Adversarial Training with Noisy Labels pdf

Hongxia Yang, Masashi Sugiyama, Jingfeng Zhang, 2021, ArXiv.

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels pdf

Mingming Gong, Masashi Sugiyama, Tongliang Liu, 2021, ICLR.

Estimation of Squared-Loss Mutual Information from Positive and Unlabeled Data pdf

Gang Niu, Tomoya Sakai, Masashi Sugiyama, 2017, ArXiv.

FedMT: Federated Learning with Mixed-type Labels

A. Talhouk, Gang Niu, Qiong Zhang, 2022, ArXiv.

On the Effectiveness of Adversarial Training against Backdoor Attacks

Masashi Sugiyama, M. Sugiyama, Gang Niu, 2022, IEEE transactions on neural networks and learning systems.

Masking: A New Perspective of Noisy Supervision

Ivor W. Tsang, Gang Niu, Masashi Sugiyama, 2018, NeurIPS.

SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning pdf

Gang Niu, Bo Han, Guodong Long, 2020, Trans. Mach. Learn. Res..

Understanding and Improving Early Stopping for Learning with Noisy Labels pdf

Erkun Yang, Yanhua Yang, Tongliang Liu, 2021, NeurIPS.

Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning

Masashi Sugiyama, Jianxiong Xiao, M. Sugiyama, 2023, NeurIPS.

PiCO: Contrastive Label Disambiguation for Partial Label Learning

Gang Niu, Yixuan Li, Gang Chen, 2022, ICLR.

CausalAdv: Adversarial Robustness through the Lens of Causality

B. Schölkopf, B. Scholkopf, Mingming Gong, 2021, 2106.06196.

Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation

Masashi Sugiyama, M. Sugiyama, Tongliang Liu, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Are Anchor Points Really Indispensable in Label-Noise Learning?

Gang Niu, Masashi Sugiyama, Chen Gong, 2019, NeurIPS.

Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network

Tongliang Liu, Bo Han, Gang Niu, 2021, ICML.

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection pdf

Gang Niu, Hanshu Yan, Jiashi Feng, 2021, ICML.

Geometry-aware Instance-reweighted Adversarial Training

Masashi Sugiyama, M. Sugiyama, Bo Han, 2020, ICLR.

Estimating Instance-dependent Label-noise Transition Matrix using DNNs pdf

Erkun Yang, Tongliang Liu, Yang Liu, 2021, ArXiv.

Class2Simi: A New Perspective on Learning with Label Noise pdf

Gang Niu, Nannan Wang, Tongliang Liu, 2020, ArXiv.

How Does Disagreement Benefit Co-teaching?

Xingrui Yu, Ivor W. Tsang, Gang Niu, 2019 .

Assessing Vulnerabilities of Adversarial Learning Algorithm through Poisoning Attacks

M. Sugiyama, Bo Han, Gang Niu, 2023, ArXiv.

A Survey of Label-noise Representation Learning: Past, Present and Future pdf

Ivor W. Tsang, James T. Kwok, Tongliang Liu, 2020, ArXiv.

Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels

Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama, 2020, ICML.

Adversarial Robustness through the Lens of Causality pdf

Bernhard Schölkopf, Mingming Gong, Xinmei Tian, 2022, ICLR.

Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack

Bo Han, Gang Niu, Feng Liu, 2022, ICML.

Confidence Scores Make Instance-dependent Label-noise Learning Possible

Gang Niu, Masashi Sugiyama, Tongliang Liu, 2019, ICML.

Rethinking Class-Prior Estimation for Positive-Unlabeled Learning

Masashi Sugiyama, M. Sugiyama, D. Tao, 2020, ICLR.

Guided Interpolation for Adversarial Training pdf

Gang Niu, Chen Chen, Masashi Sugiyama, 2021, ArXiv.

Reliable Adversarial Distillation with Unreliable Teachers

Jingren Zhou, Tongliang Liu, Bo Han, 2021, ICLR.

Logit Clipping for Robust Learning against Label Noise

Yixuan Li, Gang Niu, Lei Feng, 2022, ArXiv.

Understanding (Generalized) Label Smoothing when Learning with Noisy Labels

Tongliang Liu, Gang Niu, Jiaheng Wei, 2021, ArXiv.

Provably End-to-end Label-Noise Learning without Anchor Points

Masashi Sugiyama, M. Sugiyama, Tongliang Liu, 2021, ICML.

Active Feature Acquisition with Supervised Matrix Completion

Gang Niu, Miao Xu, Masashi Sugiyama, 2018, KDD.

Butterfly: Robust One-step Approach towards Wildly-unsupervised Domain Adaptation

Gang Niu, Masashi Sugiyama, Guangquan Zhang, 2019 .

Fast and Robust Rank Aggregation against Model Misspecification pdf

Ivor W. Tsang, Gang Niu, Masashi Sugiyama, 2019, ArXiv.

Large-Margin Contrastive Learning with Distance Polarization Regularizer

Gang Niu, Chen Gong, Shuo Chen, 2021, ICML.

Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning pdf

Gang Niu, Yu Yao, Tongliang Liu, 2020, NeurIPS.

Demystifying Assumptions in Learning to Discover Novel Classes

Long Lan, Masashi Sugiyama, Tongliang Liu, 2021 .

Local Reweighting for Adversarial Training pdf

Bo Han, Feng Liu, Gang Niu, 2021, ArXiv.

Learning Diverse-Structured Networks for Adversarial Robustness pdf

Gang Niu, Junzhou Huang, Masashi Sugiyama, 2021, ICML.

NoiLIn: Do Noisy Labels Always Hurt Adversarial Training? pdf

Masashi Sugiyama, Lizhen Cui, Jingfeng Zhang, 2021, ArXiv.

GEOMETRY-AWARE INSTANCE-REWEIGHTED ADVER-

Mohan S. Kankanhalli, M. Sugiyama, Bo Han, 2020 .

Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels

Mingming Gong, Tongliang Liu, Bo Han, 2020, ICML.

Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation

Masashi Sugiyama, M. Sugiyama, Mingming Gong, 2023, ICML.

Matrix Co-completion for Multi-label Classification with Missing Features and Labels pdf

Ivor W. Tsang, Gang Niu, Miao Xu, 2018, ArXiv.

Butterfly: A Panacea for All Difficulties in Wildly Unsupervised Domain Adaptation pdf

Gang Niu, Masashi Sugiyama, Guangquan Zhang, 2019, ArXiv.

Analysis and Improvement of Policy Gradient Estimation

Gang Niu, Masashi Sugiyama, Tingting Zhao, 2011, NIPS.

Active Refinement for Multi-Label Learning: A Pseudo-Label Approach pdf

Gang Niu, Miao Xu, Masashi Sugiyama, 2021, ArXiv.

Complementary-Label Learning for Arbitrary Losses and Models

Gang Niu, Masashi Sugiyama, Takashi Ishida, 2018, ICML.

Class-Wise Denoising for Robust Learning Under Label Noise

Masashi Sugiyama, M. Sugiyama, D. Tao, 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Towards Effective Visual Representations for Partial-Label Learning

Gang Niu, Jiaqi Lv, Xin Geng, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data

Masashi Sugiyama, A. Menon, Gang Niu, 2018, ICLR.

Classification from Pairwise Similarity and Unlabeled Data

Gang Niu, Masashi Sugiyama, Han Bao, 2018, ICML.

Exploiting Class Activation Value for Partial-Label Learning

Masashi Sugiyama, M. Sugiyama, Tongliang Liu, 2022, ICLR.

Multiple-Instance Learning from Similar and Dissimilar Bags

Gang Niu, Tao Xiang, Senlin Shu, 2021, KDD.

A Universal Unbiased Method for Classification from Aggregate Observations

Tongliang Liu, Bo Han, Gang Niu, 2023, ICML.

Making Binary Classification from Multiple Unlabeled Datasets Almost Free of Supervision

Masashi Sugiyama, Tongliang Liu, Bo Han, 2023, ArXiv.

Searching to Exploit Memorization Effect in Learning from Corrupted Labels

Bo Han, Quanming Yao, Gang Niu, 2019, ArXiv.

Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model pdf

Gang Niu, Chen Gong, Tongliang Liu, 2021, AAAI.

Fast and Robust Rank Aggregation against Model Misspecification

Masashi Sugiyama, I. Tsang, Gang Niu, 2019, J. Mach. Learn. Res..

Instance Correction for Learning with Open-set Noisy Labels pdf

Mingming Gong, Masashi Sugiyama, Tongliang Liu, 2021, ArXiv.

Semi-supervised AUC optimization based on positive-unlabeled learning

Gang Niu, Tomoya Sakai, Masashi Sugiyama, 2017, Machine Learning.

Fairness Improves Learning from Noisily Labeled Long-Tailed Data

Masashi Sugiyama, Tongliang Liu, Gang Niu, 2023, ArXiv.

Pointwise Binary Classification with Pairwise Confidence Comparisons

Masashi Sugiyama, Bo Han, Gang Niu, 2020, ICML.

Multi-Class Classification from Noisy-Similarity-Labeled Data pdf

Gang Niu, Tongliang Liu, Bo Han, 2020, ArXiv.

Uncoupled Regression from Pairwise Comparison Data

Masashi Sugiyama, Niu Gang, Junya Honda, 2019, NeurIPS.

Information-Theoretic Representation Learning for Positive-Unlabeled Classification

Gang Niu, Masashi Sugiyama, Tomoya Sakai, 2017, Neural Computation.

Beyond the Low-density Separation Principle: A Novel Approach to Semi-supervised Learning pdf

Gang Niu, Tomoya Sakai, Masashi Sugiyama, 2016, ArXiv.

Boundary-restricted metric learning

Masashi Sugiyama, Gang Niu, Shuo Chen, 2023, Machine Learning.

Distribution Shift Matters for Knowledge Distillation with Webly Collected Images

Masashi Sugiyama, Gang Niu, Shuo Chen, 2023, ArXiv.

Co-teaching: Robust training of deep neural networks with extremely noisy labels

Masashi Sugiyama, I. Tsang, Bo Han, 2018, NeurIPS.

Binary Classification with Confidence Difference

Gang Niu, Wei Wang, Lei Feng, 2023, NeurIPS.

Mitigating Memorization of Noisy Labels by Clipping the Model Prediction

Yixuan Li, Gang Niu, Lei Feng, 2022, ICML.

Learning and Mining with Noisy Labels

Masashi Sugiyama, Tongliang Liu, Bo Han, 2022, CIKM.

Butterfly: Robust One-step Approach towards Wildly-unsupervised Domain Adaptation

Masashi Sugiyama, Bo Han, Jie Lu, 2019 .

Revisiting Sample Selection Approach to Positive-Unlabeled Learning: Turning Unlabeled Data into Positive rather than Negative pdf

Gang Niu, Miao Xu, Masashi Sugiyama, 2019, ArXiv.

Pumpout: A Meta Approach to Robust Deep Learning with Noisy Labels

Xingrui Yu, Gang Niu, Miao Xu, 2018, 1809.11008.

Pumpout: A Meta Approach for Robustly Training Deep Neural Networks with Noisy Labels pdf

Xingrui Yu, Ivor W. Tsang, Gang Niu, 2018, ArXiv.

Part-dependent Label Noise: Towards Instance-dependent Label Noise

Masashi Sugiyama, Gang Niu, Xiaobo Xia, 2020, NeurIPS.

Classification from Pairwise Similarity and Unlabeled Data

Masashi Sugiyama, Gang Niu, Han Bao, 2018, ICML.

Clustering Unclustered Data: Unsupervised Binary Labeling of Two Datasets Having Different Class Balances

Masashi Sugiyama, Marthinus Christoffel du Plessis, Masashi Sugiyama, 2013, 2013 Conference on Technologies and Applications of Artificial Intelligence.

How does Disagreement Help Generalization against Label Corruption?

Masashi Sugiyama, I. Tsang, Bo Han, 2019, ICML.

Where is the Bottleneck of Adversarial Learning with Unlabeled Data? pdf

Gang Niu, Masashi Sugiyama, Bo Han, 2019, ArXiv.

Learning Intention-Aware Policies in Deep Reinforcement Learning

Masashi Sugiyama, Gang Niu, Tingting Zhao, 2023, Neural Computation.

Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning

Masashi Sugiyama, Yarui Chen, Gang Niu, 2022, Neural Networks.

Atom-Motif Contrastive Transformer for Molecular Property Prediction

Gang Niu, Wentao Yu, Chen Gong, 2023, ArXiv.

Mode-Seeking Clustering and Density Ridge Estimation via Direct Estimation of Density-Derivative-Ratios

Gang Niu, Takafumi Kanamori, Aapo Hyvärinen, 2017, J. Mach. Learn. Res..

Suffcient Component Analysis

Masashi Sugiyama, M. Yamada, Gang Niu, 2011, ACML.

Maximum Mean Discrepancy Test is Aware of Adversarial Attacks

Masashi Sugiyama, Tongliang Liu, Bo Han, 2020, ICML.

Sufficient Component Analysis for Supervised Dimension Reduction

Gang Niu, Masashi Sugiyama, Makoto Yamada, 2011, 1103.4998.

Probabilistic Margins for Instance Reweighting in Adversarial Training

Masashi Sugiyama, Mingyuan Zhou, Tongliang Liu, 2021, NeurIPS.

Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks

Masashi Sugiyama, Tongliang Liu, Bo Han, 2022, NeurIPS.

Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical

Gang Niu, Takashi Ishida, Wei Wang, 2023, 2311.15502.

Learning with Complementary Labels Revisited: A Consistent Approach via Negative-Unlabeled Learning

Gang Niu, Takashi Ishida, Wei Wang, 2023, ArXiv.

SIGUA: Forgetting May Make Learning with Noisy Labels More Robust

Masashi Sugiyama, I. Tsang, Bo Han, 2018, ICML.

Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation

Masashi Sugiyama, Gang Niu, Jiangchao Yao, 2023, NeurIPS.

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

Masashi Sugiyama, M. Sugiyama, Mingming Gong, 2021, International Conference on Learning Representations.

Learning and Mining with Noisy Labels

Masashi Sugiyama, Tongliang Liu, Bo Han, 2022, CIKM.

Bayesian Maximum Margin Clustering

Gang Niu, Bo Dai, Bao-Gang Hu, 2010, 2010 IEEE International Conference on Data Mining.

Information-Theoretic Representation Learning for Positive-Unlabeled Classification

Masashi Sugiyama, Gang Niu, Tomoya Sakai, 2017, Neural Computation.