← Authors

Gang Niu

108 papers · 2011–2026 · 11 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (25) πŸƒ Academic Marathon (14) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (11) 🌈 Renaissance Researcher (5) 🐝 Cross-Pollinator (13) πŸŒ‰ Interdisciplinary Bridge 🏠 Conference Loyalist (27) πŸ† Keyword Champion (4) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (11) 🀝 Dynamic Duo (87) πŸ† Grand Slam πŸ’Ž Century Club (107) πŸ“ˆ Trend Setter ❓ The Questioner (7) πŸš€ Conference Pioneer ⚑ Prolific Year (6) πŸ”₯ Unstoppable (13) πŸ—ƒοΈ Keyword Collector (100)

Conferences

ICML (41) NIPS (27) ICLR (17) ACML (4) JMLR (4) AAAI (3) AISTATS (3) CVPR (3) ICCV (3) ECCV (2) EACL (1)

Top co-authors

Masashi Sugiyama (88) Bo Han (42) Tongliang Liu (29) Lei Feng (13) Jingfeng ZHANG (10) Mingming Gong (9) Chen Gong (8) Nan Lu (7) Takashi Ishida (6) Miao Xu (6)

Keywords

weakly supervised learning (17) label noise (14) noisy label (10) binary classification (9) deep neural network (7) semi-supervised learning (6) noisy label learning (6) multi-class classification (6) contrastive learning (6) representation learning (5) adversarial training (5) positive-unlabeled learning (5) transition matrix (5) adversarial robustness (5) partial-label learning (4) classification risk (4) distribution shift (4) empirical risk minimization (4) risk estimation (4) unlabeled datum (4)

Papers

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