Gang Niu

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Multi-Label Knowledge Distillation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Distribution Shift Matters for Knowledge Distillation with Webly Collected Images.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Towards Effective Visual Representations for Partial-Label Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

NoiLin: Improving adversarial training and correcting stereotype of noisy labels.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2022

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

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2022

Learning from Noisy Pairwise Similarity and Unlabeled Data.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2022

Fast and Robust Rank Aggregation against Model Misspecification.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2022

Logit Clipping for Robust Learning against Label Noise.

[BibT_eX]

[DOI]

CoRR, 2022

FedMT: Federated Learning with Mixed-type Labels.

[BibT_eX]

[DOI]

CoRR, 2022

On the Effectiveness of Adversarial Training against Backdoor Attacks.

[BibT_eX]

[DOI]

CoRR, 2022

Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Learning Contrastive Embedding in Low-Dimensional Space.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

To Smooth or Not? When Label Smoothing Meets Noisy Labels.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

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

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Reliable Adversarial Distillation with Unreliable Teachers.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Adversarial Robustness Through the Lens of Causality.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Exploiting Class Activation Value for Partial-Label Learning.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Rethinking Class-Prior Estimation for Positive-Unlabeled Learning.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

PiCO: Contrastive Label Disambiguation for Partial Label Learning.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Federated Learning from Only Unlabeled Data with Class-conditional-sharing Clients.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

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

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Learning and Mining with Noisy Labels.

[BibT_eX]

[DOI]

Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

2021

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

[BibT_eX]

[DOI]

Neural Comput., 2021

Information-Theoretic Representation Learning for Positive-Unlabeled Classification.

[BibT_eX]

[DOI]

Neural Comput., 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

Local Reweighting for Adversarial Training.

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

On the Robustness of Average Losses for Partial-Label Learning.

[BibT_eX]

[DOI]

CoRR, 2021

Understanding (Generalized) Label Smoothing when Learning with Noisy Labels.

[BibT_eX]

[DOI]

CoRR, 2021

Instance Correction for Learning with Open-set Noisy Labels.

[BibT_eX]

[DOI]

CoRR, 2021

NoiLIn: Do Noisy Labels Always Hurt Adversarial Training?

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

Guided Interpolation for Adversarial Training.

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

Understanding the Interaction of Adversarial Training with Noisy Labels.

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Probabilistic Margins for Instance Reweighting in Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Understanding and Improving Early Stopping for Learning with Noisy Labels.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Multiple-Instance Learning from Similar and Dissimilar Bags.

[BibT_eX]

[DOI]

Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

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

[BibT_eX]

[DOI]

Yivan Zhang

Proceedings of the 38th International Conference on Machine Learning, 2021

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

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Provably End-to-end Label-noise Learning without Anchor Points.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Maximum Mean Discrepancy Test is Aware of Adversarial Attacks.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Pointwise Binary Classification with Pairwise Confidence Comparisons.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Learning Diverse-Structured Networks for Adversarial Robustness.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Learning from Similarity-Confidence Data.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Confidence Scores Make Instance-dependent Label-noise Learning Possible.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Large-Margin Contrastive Learning with Distance Polarization Regularizer.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Geometry-aware Instance-reweighted Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning.

[BibT_eX]

[DOI]

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, 2021

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

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

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

[BibT_eX]

[DOI]

CoRR, 2020

Maximum Mean Discrepancy is Aware of Adversarial Attacks.

[BibT_eX]

[DOI]

CoRR, 2020

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

[BibT_eX]

[DOI]

CoRR, 2020

Class2Simi: A New Perspective on Learning with Label Noise.

[BibT_eX]

[DOI]

CoRR, 2020

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

[BibT_eX]

[DOI]

CoRR, 2020

Towards Mixture Proportion Estimation without Irreducibility.

[BibT_eX]

[DOI]

CoRR, 2020

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Provably Consistent Partial-Label Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Rethinking Importance Weighting for Deep Learning under Distribution Shift.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Attacks Which Do Not Kill Training Make Adversarial Learning Stronger.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Searching to Exploit Memorization Effect in Learning with Noisy Labels.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Progressive Identification of True Labels for Partial-Label Learning.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

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

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Learning with Multiple Complementary Labels.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

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

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

SIGUA: Forgetting May Make Learning with Noisy Labels More Robust.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

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

[BibT_eX]

[DOI]

Proceedings of the 20th IEEE International Conference on Data Mining, 2020

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

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

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

[BibT_eX]

[DOI]

Chao Li

Mohammad Emtiyaz Khan

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Where is the Bottleneck of Adversarial Learning with Unlabeled Data?

[BibT_eX]

[DOI]

CoRR, 2019

Searching to Exploit Memorization Effect in Learning from Corrupted Labels.

[BibT_eX]

[DOI]

CoRR, 2019

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

[BibT_eX]

[DOI]

CoRR, 2019

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

[BibT_eX]

[DOI]

CoRR, 2019

Uncoupled Regression from Pairwise Comparison Data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Are Anchor Points Really Indispensable in Label-Noise Learning?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

How does Disagreement Help Generalization against Label Corruption?

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Complementary-Label Learning for Arbitrary Losses and Models.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Classification from Positive, Unlabeled and Biased Negative Data.

[BibT_eX]

[DOI]

Yu-Guan Hsieh

Proceedings of the 36th International Conference on Machine Learning, 2019

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

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

Sufficient Dimension Reduction via Direct Estimation of the Gradients of Logarithmic Conditional Densities.

[BibT_eX]

[DOI]

Neural Comput., 2018

Correction to: Semi-supervised AUC optimization based on positive-unlabeled learning.

[BibT_eX]

[DOI]

Mach. Learn., 2018

Semi-supervised AUC optimization based on positive-unlabeled learning.

[BibT_eX]

[DOI]

Mach. Learn., 2018

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

[BibT_eX]

[DOI]

CoRR, 2018

Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data.

[BibT_eX]

[DOI]

CoRR, 2018

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

[BibT_eX]

[DOI]

CoRR, 2018

Co-sampling: Training Robust Networks for Extremely Noisy Supervision.

[BibT_eX]

[DOI]

CoRR, 2018

Binary Classification from Positive-Confidence Data.

[BibT_eX]

[DOI]

Takashi Ishida

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Masking: A New Perspective of Noisy Supervision.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Active Feature Acquisition with Supervised Matrix Completion.

[BibT_eX]

[DOI]

Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018

Does Distributionally Robust Supervised Learning Give Robust Classifiers?

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Classification from Pairwise Similarity and Unlabeled Data.

[BibT_eX]

[DOI]

Han Bao

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

Class-prior estimation for learning from positive and unlabeled data.

[BibT_eX]

[DOI]

Mach. Learn., 2017

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

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2017

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

[BibT_eX]

[DOI]

CoRR, 2017

Learning from Complementary Labels.

[BibT_eX]

[DOI]

Takashi Ishida

CoRR, 2017

Positive-Unlabeled Learning with Non-Negative Risk Estimator.

[BibT_eX]

[DOI]

Ryuichi Kiryo

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Learning from Complementary Labels.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

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

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

Whitening-Free Least-Squares Non-Gaussian Component Analysis.

[BibT_eX]

[DOI]

Proceedings of The 9th Asian Conference on Machine Learning, 2017

2016

Direct Density Derivative Estimation.

[BibT_eX]

[DOI]

Neural Comput., 2016

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

[BibT_eX]

[DOI]

CoRR, 2016

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

[BibT_eX]

[DOI]

CoRR, 2016

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

[BibT_eX]

[DOI]

Yao Ma

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Non-Gaussian Component Analysis with Log-Density Gradient Estimation.

[BibT_eX]

[DOI]

Hiroaki Sasaki

Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

2015

Convex Formulation for Learning from Positive and Unlabeled Data.

[BibT_eX]

[DOI]

Proceedings of the 32nd International Conference on Machine Learning, 2015

Regularized Policy Gradients: Direct Variance Reduction in Policy Gradient Estimation.

[BibT_eX]

[DOI]

Proceedings of The 7th Asian Conference on Machine Learning, 2015

2014

Semi-supervised information-maximization clustering.

[BibT_eX]

[DOI]

Daniele Calandriello

Neural Networks, 2014

Information-Maximization Clustering Based on Squared-Loss Mutual Information.

[BibT_eX]

[DOI]

Neural Comput., 2014

Information-Theoretic Semi-Supervised Metric Learning via Entropy Regularization.

[BibT_eX]

[DOI]

Neural Comput., 2014

Analysis of Learning from Positive and Unlabeled Data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Transductive Learning with Multi-class Volume Approximation.

[BibT_eX]

[DOI]

Bo Dai

Proceedings of the 31th International Conference on Machine Learning, 2014

2013

Maximum volume clustering: a new discriminative clustering approach.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2013

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

[BibT_eX]

[DOI]

Proceedings of the Conference on Technologies and Applications of Artificial Intelligence, 2013

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

[BibT_eX]

[DOI]

Proceedings of the 30th International Conference on Machine Learning, 2013

2012

Analysis and improvement of policy gradient estimation.

[BibT_eX]

[DOI]

Neural Networks, 2012

2011

Suffcient Component Analysis.

[BibT_eX]

[DOI]

Proceedings of the 3rd Asian Conference on Machine Learning, 2011

Maximum Volume Clustering.

[BibT_eX]

[DOI]

Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

Transfer Learning via Multi-View Principal Component Analysis.

[BibT_eX]

[DOI]

J. Comput. Sci. Technol., 2011

2010

Rough Margin Based Core Vector Machine.

[BibT_eX]

[DOI]

Proceedings of the Advances in Knowledge Discovery and Data Mining, 2010

Compact Margin Machine.

[BibT_eX]

[DOI]

Bo Dai

Proceedings of the Advances in Knowledge Discovery and Data Mining, 2010

Bayesian Maximum Margin Clustering.

[BibT_eX]

[DOI]

Bo Dai

Bao-Gang Hu