Gang Niu
#177,804
Most Influential Person Now
Gang Niu's AcademicInfluence.com Rankings
Gang Niucomputer-science Degrees
Computer Science
#11097
World Rank
#11723
Historical Rank
Algorithms
#454
World Rank
#460
Historical Rank
Machine Learning
#5073
World Rank
#5136
Historical Rank
Artificial Intelligence
#5471
World Rank
#5546
Historical Rank

Download Badge
Computer Science
Gang Niu's Degrees
- Bachelors Computer Science Peking University
Similar Degrees You Can Earn
Why Is Gang Niu Influential?
(Suggest an Edit or Addition)Gang Niu's Published Works
Number of citations in a given year to any of this author's works
Total number of citations to an author for the works they published in a given year. This highlights publication of the most important work(s) by the author
Published Works
- Co-teaching: Robust training of deep neural networks with extremely noisy labels (2018) (1177)
- How does Disagreement Help Generalization against Label Corruption? (2019) (427)
- Positive-Unlabeled Learning with Non-Negative Risk Estimator (2017) (300)
- Analysis of Learning from Positive and Unlabeled Data (2014) (283)
- Convex Formulation for Learning from Positive and Unlabeled Data (2015) (243)
- Attacks Which Do Not Kill Training Make Adversarial Learning Stronger (2020) (228)
- Are Anchor Points Really Indispensable in Label-Noise Learning? (2019) (205)
- Does Distributionally Robust Supervised Learning Give Robust Classifiers? (2016) (186)
- Masking: A New Perspective of Noisy Supervision (2018) (179)
- Geometry-aware Instance-reweighted Adversarial Training (2020) (136)
- Class-prior estimation for learning from positive and unlabeled data (2016) (129)
- Parts-dependent Label Noise: Towards Instance-dependent Label Noise (2020) (121)
- Analysis and Improvement of Policy Gradient Estimation (2011) (119)
- Learning from Complementary Labels (2017) (106)
- Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning (2020) (102)
- Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning (2016) (94)
- SIGUA: Forgetting May Make Learning with Noisy Labels More Robust (2018) (84)
- Information-Theoretic Semi-Supervised Metric Learning via Entropy Regularization (2012) (84)
- Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data (2016) (79)
- Progressive Identification of True Labels for Partial-Label Learning (2020) (78)
- A Survey of Label-noise Representation Learning: Past, Present and Future (2020) (78)
- On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data (2018) (65)
- Do We Need Zero Training Loss After Achieving Zero Training Error? (2020) (65)
- Complementary-Label Learning for Arbitrary Losses and Models (2018) (64)
- Classification from Pairwise Similarity and Unlabeled Data (2018) (61)
- Searching to Exploit Memorization Effect in Learning with Noisy Labels (2020) (56)
- Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations (2021) (56)
- Rethinking Importance Weighting for Deep Learning under Distribution Shift (2020) (55)
- Learning with Multiple Complementary Labels (2020) (55)
- Provably Consistent Partial-Label Learning (2020) (52)
- Confidence Scores Make Instance-dependent Label-noise Learning Possible (2019) (50)
- Classification from Positive, Unlabeled and Biased Negative Data (2018) (48)
- Provably End-to-end Label-Noise Learning without Anchor Points (2021) (47)
- Understanding and Improving Early Stopping for Learning with Noisy Labels (2021) (45)
- Semi-supervised AUC optimization based on positive-unlabeled learning (2017) (43)
- Information-Maximization Clustering Based on Squared-Loss Mutual Information (2011) (42)
- PiCO: Contrastive Label Disambiguation for Partial Label Learning (2022) (40)
- Squared-loss Mutual Information Regularization: A Novel Information-theoretic Approach to Semi-supervised Learning (2013) (38)
- Active Feature Acquisition with Supervised Matrix Completion (2018) (36)
- Binary Classification from Positive-Confidence Data (2017) (34)
- Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels (2020) (31)
- Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach (2019) (31)
- Sample Selection with Uncertainty of Losses for Learning with Noisy Labels (2021) (31)
- Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization (2021) (29)
- Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels (2020) (26)
- Maximum Mean Discrepancy Test is Aware of Adversarial Attacks (2020) (25)
- How Does Disagreement Benefit Co-teaching? (2019) (25)
- Adversarial Robustness through the Lens of Causality (2022) (22)
- Estimating Instance-dependent Label-noise Transition Matrix using DNNs (2021) (21)
- Butterfly: A Panacea for All Difficulties in Wildly Unsupervised Domain Adaptation (2019) (21)
- Instance-dependent Label-noise Learning under a Structural Causal Model (2021) (20)
- Transfer Learning via Multi-View Principal Component Analysis (2011) (19)
- Computationally efficient sufficient dimension reduction via squared-loss mutual information (2011) (18)
- Clustering Unclustered Data: Unsupervised Binary Labeling of Two Datasets Having Different Class Balances (2013) (18)
- Pumpout: A Meta Approach for Robustly Training Deep Neural Networks with Noisy Labels (2018) (17)
- Class2Simi: A New Perspective on Learning with Label Noise (2020) (16)
- Large-Margin Contrastive Learning with Distance Polarization Regularizer (2021) (16)
- Non-Gaussian Component Analysis with Log-Density Gradient Estimation (2015) (16)
- Probabilistic Margins for Instance Reweighting in Adversarial Training (2021) (15)
- Semi-supervised information-maximization clustering (2013) (14)
- CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection (2021) (14)
- Understanding the Interaction of Adversarial Training with Noisy Labels (2021) (14)
- Maximum Mean Discrepancy is Aware of Adversarial Attacks (2020) (14)
- Reliable Adversarial Distillation with Unreliable Teachers (2021) (13)
- Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data (2018) (13)
- Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients (2022) (13)
- Co-sampling: Training Robust Networks for Extremely Noisy Supervision (2018) (12)
- Matrix Co-completion for Multi-label Classification with Missing Features and Labels (2018) (12)
- Understanding (Generalized) Label Smoothing when Learning with Noisy Labels (2021) (12)
- Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation (2022) (12)
- Maximum volume clustering: a new discriminative clustering approach (2013) (11)
- Direct Density Derivative Estimation (2016) (11)
- Learning Diverse-Structured Networks for Adversarial Robustness (2021) (10)
- To Smooth or Not? When Label Smoothing Meets Noisy Labels (2021) (10)
- Revisiting Sample Selection Approach to Positive-Unlabeled Learning: Turning Unlabeled Data into Positive rather than Negative (2019) (10)
- Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model (2021) (10)
- Regularized Policy Gradients: Direct Variance Reduction in Policy Gradient Estimation (2015) (10)
- Exploiting Class Activation Value for Partial-Label Learning (2022) (10)
- Searching to Exploit Memorization Effect in Learning from Corrupted Labels (2019) (9)
- Meta Discovery: Learning to Discover Novel Classes given Very Limited Data (2021) (9)
- Guided Interpolation for Adversarial Training (2021) (9)
- Uncoupled Regression from Pairwise Comparison Data (2019) (8)
- On the Robustness of Average Losses for Partial-Label Learning (2021) (8)
- Multi-Class Classification from Noisy-Similarity-Labeled Data (2020) (8)
- CausalAdv: Adversarial Robustness through the Lens of Causality (2021) (8)
- SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning (2020) (8)
- Pumpout: A Meta Approach to Robust Deep Learning with Noisy Labels (2018) (7)
- Instance Correction for Learning with Open-set Noisy Labels (2021) (7)
- A Pseudo-Label Method for Coarse-to-Fine Multi-Label Learning with Limited Supervision (2019) (7)
- Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition Under Reshuffling (2018) (7)
- Towards Mixture Proportion Estimation without Irreducibility (2020) (7)
- Multiple-Instance Learning from Similar and Dissimilar Bags (2021) (6)
- Pointwise Binary Classification with Pairwise Confidence Comparisons (2020) (6)
- Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification (2021) (5)
- Rethinking Class-Prior Estimation for Positive-Unlabeled Learning (2020) (5)
- Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning (2019) (5)
- Where is the Bottleneck of Adversarial Learning with Unlabeled Data? (2019) (5)
- Beyond the Low-density Separation Principle: A Novel Approach to Semi-supervised Learning (2016) (5)
- Mode-Seeking Clustering and Density Ridge Estimation via Direct Estimation of Density-Derivative-Ratios (2017) (5)
- Maximum Volume Clustering (2011) (4)
- Sufficient Dimension Reduction via Direct Estimation of the Gradients of Logarithmic Conditional Densities (2015) (4)
- Bayesian Maximum Margin Clustering (2010) (4)
- NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels (2021) (4)
- Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network (2021) (4)
- On the Effectiveness of Adversarial Training against Backdoor Attacks (2022) (4)
- Whitening-Free Least-Squares Non-Gaussian Component Analysis (2016) (3)
- Learning from Similarity-Confidence Data (2021) (3)
- SERAPH: Semi-supervised Metric Learning Paradigm with Hyper Sparsity (2011) (3)
- Cross-Graph: Robust and Unsupervised Embedding for Attributed Graphs with Corrupted Structure (2020) (2)
- Logit Clipping for Robust Learning against Label Noise (2022) (2)
- NoiLIn: Do Noisy Labels Always Hurt Adversarial Training? (2021) (2)
- Local Reweighting for Adversarial Training (2021) (2)
- Butterfly: Robust One-step Approach towards Wildly-unsupervised Domain Adaptation (2019) (2)
- PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning (2022) (2)
- Class-prior estimation for learning from positive and unlabeled data (2016) (2)
- Theoretical Comparisons of Learning from Positive-Negative, Positive-Unlabeled, and Negative-Unlabeled Data (2016) (2)
- Semi-Supervised Classification based on Positive-Unlabeled Classification (2017) (1)
- Compact Margin Machine (2010) (1)
- Information-Theoretic Representation Learning for Positive-Unlabeled Classification (2017) (1)
- Transductive Learning with Multi-class Volume Approximation (2014) (1)
- Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack (2022) (1)
- Fast and Robust Rank Aggregation against Model Misspecification (2019) (1)
- Fairness Improves Learning from Noisily Labeled Long-Tailed Data (2023) (1)
- Class-Wise Denoising for Robust Learning Under Label Noise (2022) (1)
- Sufficient Component Analysis for Supervised Dimension Reduction (2011) (1)
- Multi-Class Classification from Single-Class Data with Confidences (2021) (1)
- GEOMETRY-AWARE INSTANCE-REWEIGHTED ADVER- (2020) (1)
- Revisiting Distributionally Robust Supervised Learning in Classification (2016) (1)
- Demystifying Assumptions in Learning to Discover Novel Classes (2021) (0)
- Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses (2022) (0)
- F EDERATED L EARNING FROM O NLY U NLABELED D ATA WITH C LASS -C ONDITIONAL -S HARING C LIENTS (2022) (0)
- Learning from Noisy Pairwise Similarity and Unlabeled Data (2022) (0)
- Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning (2023) (0)
- S2GA: Robust Deep Learning with Noisy Labels without Early Stopping (2020) (0)
- Suffcient Component Analysis (2011) (0)
- FedMT: Federated Learning with Mixed-type Labels (2022) (0)
- Direction Matters: On Influence-Preserving Graph Summarization and Max-Cut Principle for Directed Graphs (2019) (0)
- Semi-supervised AUC optimization based on positive-unlabeled learning (2017) (0)
- Learning and Mining with Noisy Labels (2022) (0)
- Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks (2022) (0)
- Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning (2022) (0)
- Rough Margin Based Core Vector Machine (2010) (0)
- Assessing Vulnerabilities of Adversarial Learning Algorithm through Poisoning Attacks (2023) (0)
- Learning Contrastive Embedding in Low-Dimensional Space (2022) (0)
- Co-teaching + : Towards Training of Robust Deep Networks with Noisy Labels (2019) (0)
- Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification (2022) (0)
- Active Refinement for Multi-Label Learning: A Pseudo-Label Approach (2021) (0)
- Estimation of Squared-Loss Mutual Information from Positive and Unlabeled Data (2017) (0)
- Wildly Unsupervised Domain Adaptation and Its Powerful and Efficient Solution (2019) (0)
This paper list is powered by the following services: