Gang Niu

Robust Learning from Noisily Labeled Long-Tailed Data via Fairness Regularizer AAAI 2026 Adaptive Localization of Knowledge Negation for Continual LLM Unlearning ICML 2025 Learning View-invariant World Models for Visual Robotic Manipulation ICLR 2025 Learning without Isolation: Pathway Protection for Continual Learning ICML 2025 On the Role of Label Noise in the Feature Learning Process ICML 2025 Realistic Evaluation of Deep Partial-Label Learning Algorithms ICLR 2025 Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation ICCV 2025 Towards Out-of-Modal Generalization without Instance-level Modal Correspondence ICLR 2025 Accurate Forgetting for Heterogeneous Federated Continual Learning ICLR 2024 Balancing Similarity and Complementarity for Federated Learning ICML 2024 Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training ICML 2024 Direct Distillation between Different Domains ECCV 2024 Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning ECCV 2024 Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought ICML 2024 Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios CVPR 2024 Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical ICML 2024 Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization ICML 2024 Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization NeurIPS 2024 Robust Similarity Learning with Difference Alignment Regularization ICLR 2024 What Makes Partial-Label Learning Algorithms Effective? NeurIPS 2024 A Universal Unbiased Method for Classification from Aggregate Observations ICML 2023 Binary Classification with Confidence Difference NeurIPS 2023 Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning NeurIPS 2023 Distribution Shift Matters for Knowledge Distillation with Webly Collected Images ICCV 2023 Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation NeurIPS 2023 Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation ICML 2023 Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems NeurIPS 2023 Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification ICLR 2023 Mitigating Memorization of Noisy Labels by Clipping the Model Prediction ICML 2023 Multi-Label Knowledge Distillation ICCV 2023 Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration NeurIPS 2023 Towards Effective Visual Representations for Partial-Label Learning CVPR 2023 Adversarial Robustness Through the Lens of Causality ICLR 2022 Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks NeurIPS 2022 Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network ICML 2022 Exploiting Class Activation Value for Partial-Label Learning ICLR 2022 Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack ICML 2022 Fast and Robust Rank Aggregation against Model Misspecification JMLR 2022 Federated Learning from Only Unlabeled Data with Class-conditional-sharing Clients ICLR 2022 Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses NeurIPS 2022 Instance-Dependent Label-Noise Learning With Manifold-Regularized Transition Matrix Estimation CVPR 2022 Learning Contrastive Embedding in Low-Dimensional Space NeurIPS 2022 Learning from Noisy Pairwise Similarity and Unlabeled Data JMLR 2022 Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations ICLR 2022 Meta Discovery: Learning to Discover Novel Classes given Very Limited Data ICLR 2022 PiCO: Contrastive Label Disambiguation for Partial Label Learning ICLR 2022 Reliable Adversarial Distillation with Unreliable Teachers ICLR 2022 Rethinking Class-Prior Estimation for Positive-Unlabeled Learning ICLR 2022 Sample Selection with Uncertainty of Losses for Learning with Noisy Labels ICLR 2022 To Smooth or Not? When Label Smoothing Meets Noisy Labels ICML 2022 Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification ICML 2021 CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection ICML 2021 Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels ICML 2021 Confidence Scores Make Instance-dependent Label-noise Learning Possible ICML 2021 Geometry-aware Instance-reweighted Adversarial Training ICLR 2021 Instance-dependent Label-noise Learning under a Structural Causal Model NeurIPS 2021 Large-Margin Contrastive Learning with Distance Polarization Regularizer ICML 2021 Learning Diverse-Structured Networks for Adversarial Robustness ICML 2021 Learning from Similarity-Confidence Data ICML 2021 Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization ICML 2021 Maximum Mean Discrepancy Test is Aware of Adversarial Attacks ICML 2021 Pointwise Binary Classification with Pairwise Confidence Comparisons ICML 2021 Probabilistic Margins for Instance Reweighting in Adversarial Training NeurIPS 2021 Provably End-to-end Label-noise Learning without Anchor Points ICML 2021 Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning EACL 2021 Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model AAAI 2021 Understanding and Improving Early Stopping for Learning with Noisy Labels NeurIPS 2021 Attacks Which Do Not Kill Training Make Adversarial Learning Stronger ICML 2020 Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition Under Reshuffling AAAI 2020 Do We Need Zero Training Loss After Achieving Zero Training Error? ICML 2020 Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning NeurIPS 2020 Learning with Multiple Complementary Labels ICML 2020 Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach AISTATS 2020 Part-dependent Label Noise: Towards Instance-dependent Label Noise NeurIPS 2020 Progressive Identification of True Labels for Partial-Label Learning ICML 2020 Provably Consistent Partial-Label Learning NeurIPS 2020 Rethinking Importance Weighting for Deep Learning under Distribution Shift NeurIPS 2020 Searching to Exploit Memorization Effect in Learning with Noisy Labels ICML 2020 SIGUA: Forgetting May Make Learning with Noisy Labels More Robust ICML 2020 Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels ICML 2020 Are Anchor Points Really Indispensable in Label-Noise Learning? NeurIPS 2019 Classification from Positive, Unlabeled and Biased Negative Data ICML 2019 Complementary-Label Learning for Arbitrary Losses and Models ICML 2019 How does Disagreement Help Generalization against Label Corruption? ICML 2019 On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data ICLR 2019 Uncoupled Regression from Pairwise Comparison Data NeurIPS 2019 Binary Classification from Positive-Confidence Data NeurIPS 2018 Classification from Pairwise Similarity and Unlabeled Data ICML 2018 Co-teaching: Robust training of deep neural networks with extremely noisy labels NeurIPS 2018 Does Distributionally Robust Supervised Learning Give Robust Classifiers? ICML 2018 Masking: A New Perspective of Noisy Supervision NeurIPS 2018 Mode-Seeking Clustering and Density Ridge Estimation via Direct Estimation of Density-Derivative-Ratios JMLR 2018 Learning from Complementary Labels NeurIPS 2017 Positive-Unlabeled Learning with Non-Negative Risk Estimator NeurIPS 2017 Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data ICML 2017 Whitening-Free Least-Squares Non-Gaussian Component Analysis ACML 2017 Non-Gaussian Component Analysis with Log-Density Gradient Estimation AISTATS 2016 Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning NeurIPS 2016 Class-prior Estimation for Learning from Positive and Unlabeled Data ACML 2015 Convex Formulation for Learning from Positive and Unlabeled Data ICML 2015 Regularized Policy Gradients: Direct Variance Reduction in Policy Gradient Estimation ACML 2015 Analysis of Learning from Positive and Unlabeled Data NeurIPS 2014 Transductive Learning with Multi-class Volume Approximation ICML 2014 Maximum Volume Clustering: A New Discriminative Clustering Approach JMLR 2013 Squared-loss Mutual Information Regularization: A Novel Information-theoretic Approach to Semi-supervised Learning ICML 2013 Analysis and Improvement of Policy Gradient Estimation NeurIPS 2011 Computationally Efficient Sufficient Dimension Reduction via Squared-Loss Mutual Information ACML 2011 Maximum Volume Clustering AISTATS 2011