{"total":111,"rows":[{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395,"area":null},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293,"area":null},{"id":"2103.07756","title":"Learning with Feature-Dependent Label Noise: A Progressive Approach","created":"2021-03-13","cited_by_count":102,"area":null},{"id":"2311.06750","title":"Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark","created":"2023-11-12","cited_by_count":99,"area":null},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84,"area":null},{"id":"2102.11628","title":"FINE Samples for Learning with Noisy Labels","created":"2021-02-23","cited_by_count":82,"area":null},{"id":"2102.02414","title":"Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization","created":"2021-02-04","cited_by_count":62,"area":null},{"id":"2106.10891","title":"Open-set Label Noise Can Improve Robustness Against Inherent Label Noise","created":"2021-06-21","cited_by_count":59,"area":null},{"id":"2201.09637","title":"DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations","created":"2022-01-24","cited_by_count":54,"area":null},{"id":"2106.03110","title":"Asymmetric Loss Functions for Learning with Noisy Labels","created":"2021-06-06","cited_by_count":46,"area":null},{"id":"2201.12498","title":"Investigating Why Contrastive Learning Benefits Robustness Against Label Noise","created":"2022-01-29","cited_by_count":46,"area":null},{"id":"2104.08984","title":"Contrastive Learning Improves Model Robustness Under Label Noise","created":"2021-04-19","cited_by_count":36,"area":null},{"id":"2101.02839","title":"Unsupervised Domain Adaptation of Black-Box Source Models","created":"2021-01-08","cited_by_count":32,"area":null},{"id":"2110.14057","title":"Meta-learning with an Adaptive Task Scheduler","created":"2021-10-26","cited_by_count":27,"area":null},{"id":"2208.12807","title":"Towards Federated Learning against Noisy Labels via Local Self-Regularization","created":"2022-08-25","cited_by_count":26,"area":null},{"id":"2103.16047","title":"Noise-resistant Deep Metric Learning with Ranking-based Instance Selection","created":"2021-03-30","cited_by_count":23,"area":null},{"id":"2204.05494","title":"Few-shot Learning with Noisy Labels","created":"2022-04-12","cited_by_count":23,"area":null},{"id":"2106.07451","title":"Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions","created":"2021-06-14","cited_by_count":21,"area":null},{"id":"2204.09371","title":"Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification","created":"2022-04-20","cited_by_count":21,"area":null},{"id":"2502.07551","title":"Early Stopping Against Label Noise Without Validation Data","created":"2025-02-11","cited_by_count":21,"area":null},{"id":"2111.14932","title":"Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection","created":"2021-11-29","cited_by_count":20,"area":null},{"id":"2102.03482","title":"Understanding the Interaction of Adversarial Training with Noisy Labels","created":"2021-02-06","cited_by_count":19,"area":null},{"id":"2201.07951","title":"Informative Pseudo-Labeling for Graph Neural Networks with Few Labels","created":"2022-01-20","cited_by_count":19,"area":null},{"id":"2105.01798","title":"Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence","created":"2021-05-04","cited_by_count":18,"area":null},{"id":"2308.13862","title":"Late Stopping: Avoiding Confidently Learning from Mislabeled Examples","created":"2023-08-26","cited_by_count":17,"area":null},{"id":"2201.00849","title":"Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Data","created":"2021-12-30","cited_by_count":16,"area":null},{"id":"2305.18377","title":"BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning","created":"2023-05-28","cited_by_count":16,"area":null},{"id":"2410.21331","title":"Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness","created":"2024-10-27","cited_by_count":13,"area":null},{"id":"2101.05467","title":"Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model","created":"2021-01-14","cited_by_count":12,"area":null},{"id":"2109.07628","title":"Connecting Low-Loss Subspace for Personalized Federated Learning","created":"2021-09-16","cited_by_count":12,"area":null},{"id":"2205.10110","title":"FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2112.10157","title":"Rethinking Importance Weighting for Transfer Learning","created":"2021-12-19","cited_by_count":11,"area":null},{"id":"2112.14869","title":"Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity","created":"2021-12-30","cited_by_count":11,"area":null},{"id":"2305.16771","title":"Robust Nonparametric Regression under Poisoning Attack","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2312.08852","title":"ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance","created":"2023-12-13","cited_by_count":11,"area":null},{"id":"2504.02901","title":"Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLM-Powered Assistance","created":"2025-04-03","cited_by_count":11,"area":null},{"id":"2105.00349","title":"Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise","created":"2021-05-01","cited_by_count":10,"area":null},{"id":"2212.03462","title":"PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels","created":"2022-12-07","cited_by_count":10,"area":null},{"id":"2302.11121","title":"Counterfactual Prediction Under Outcome Measurement Error","created":"2023-02-22","cited_by_count":10,"area":null},{"id":"2306.17105","title":"Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2303.15833","title":"Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning","created":"2023-03-28","cited_by_count":9,"area":null},{"id":"2105.14676","title":"NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels","created":"2021-05-31","cited_by_count":8,"area":null},{"id":"2312.06273","title":"Regroup Median Loss for Combating Label Noise","created":"2023-12-11","cited_by_count":8,"area":null},{"id":"2406.17182","title":"Debiased Recommendation with Noisy Feedback","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2104.11557","title":"Knodle: Modular Weakly Supervised Learning with PyTorch","created":"2021-04-23","cited_by_count":7,"area":null},{"id":"2206.13140","title":"Compressing Features for Learning with Noisy Labels","created":"2022-06-27","cited_by_count":7,"area":null},{"id":"2105.03059","title":"Self-paced Resistance Learning against Overfitting on Noisy Labels","created":"2021-05-07","cited_by_count":6,"area":null},{"id":"2107.11972","title":"Trade When Opportunity Comes: Price Movement Forecasting via Locality-Aware Attention and Iterative Refinement Labeling","created":"2021-07-26","cited_by_count":6,"area":null},{"id":"2204.09120","title":"Optical Remote Sensing Image Understanding with Weak Supervision: Concepts, Methods, and Perspectives","created":"2022-04-18","cited_by_count":6,"area":null},{"id":"2505.06684","title":"FNBench: Benchmarking Robust Federated Learning against Noisy Labels","created":"2025-05-10","cited_by_count":6,"area":null},{"id":"2508.02387","title":"$\\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise","created":"2025-08-04","cited_by_count":6,"area":null},{"id":"2109.11282","title":"Unbiased Loss Functions for Multilabel Classification with Missing Labels","created":"2021-09-23","cited_by_count":5,"area":null},{"id":"2303.12291","title":"Fairness Improves Learning from Noisily Labeled Long-Tailed Data","created":"2023-03-22","cited_by_count":5,"area":null},{"id":"2103.11594","title":"Deep Neural Networks Learn Meta-Structures from Noisy Labels in Semantic Segmentation","created":"2021-03-22","cited_by_count":4,"area":null},{"id":"2103.12814","title":"Co-matching: Combating Noisy Labels by Augmentation Anchoring","created":"2021-03-23","cited_by_count":4,"area":null},{"id":"2104.04665","title":"On Universal Black-Box Domain Adaptation","created":"2021-04-10","cited_by_count":4,"area":null},{"id":"2106.09136","title":"Binary classification with corrupted labels","created":"2021-06-16","cited_by_count":4,"area":null},{"id":"2205.07427","title":"Exploring the Learning Difficulty of Data Theory and Measure","created":"2022-05-16","cited_by_count":4,"area":null},{"id":"2206.11602","title":"Prototype-Anchored Learning for Learning with Imperfect Annotations","created":"2022-06-23","cited_by_count":4,"area":null},{"id":"2506.12468","title":"Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2103.13569","title":"Approximating Instance-Dependent Noise via Instance-Confidence Embedding","created":"2021-03-25","cited_by_count":3,"area":null},{"id":"2104.09045","title":"Do We Really Need Gold Samples for Sample Weighting Under Label Noise?","created":"2021-04-19","cited_by_count":3,"area":null},{"id":"2203.10858","title":"Multi-class Label Noise Learning via Loss Decomposition and Centroid Estimation","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2203.14434","title":"Flexible risk design using bi-directional dispersion","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2207.11987","title":"Information Processing Equalities and the Information-Risk Bridge","created":"2022-07-25","cited_by_count":3,"area":null},{"id":"2301.07306","title":"Improve Noise Tolerance of Robust Loss via Noise-Awareness","created":"2023-01-18","cited_by_count":3,"area":null},{"id":"2103.17008","title":"Collaborative Label Correction via Entropy Thresholding","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2104.12477","title":"An Exploration into why Output Regularization Mitigates Label Noise","created":"2021-04-26","cited_by_count":2,"area":null},{"id":"2110.08866","title":"Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2112.04590","title":"The perils of being unhinged: On the accuracy of classifiers minimizing a noise-robust convex loss","created":"2021-12-08","cited_by_count":2,"area":null},{"id":"2201.12739","title":"Do We Need to Penalize Variance of Losses for Learning with Label Noise?","created":"2022-01-30","cited_by_count":2,"area":null},{"id":"2204.12155","title":"Bias-Variance Decompositions for Margin Losses","created":"2022-04-26","cited_by_count":2,"area":null},{"id":"2311.00668","title":"ProcSim: Proxy-based Confidence for Robust Similarity Learning","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2405.07083","title":"Data-Efficient and Robust Task Selection for Meta-Learning","created":"2024-05-11","cited_by_count":2,"area":null},{"id":"2410.21014","title":"Informed Deep Abstaining Classifier: Investigating noise-robust training for diagnostic decision support systems","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2604.27742","title":"Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2108.05092","title":"Cooperative Learning for Noisy Supervision","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2201.10242","title":"GMM Discriminant Analysis with Noisy Label for Each Class","created":"2022-01-25","cited_by_count":1,"area":null},{"id":"2203.16282","title":"The Weak Supervision Landscape","created":"2022-03-30","cited_by_count":1,"area":null},{"id":"2205.09628","title":"What killed the Convex Booster ?","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2206.01476","title":"Task-Adaptive Pre-Training for Boosting Learning With Noisy Labels: A Study on Text Classification for African Languages","created":"2022-06-03","cited_by_count":1,"area":null},{"id":"2212.02745","title":"Sources of Noise in Dialogue and How to Deal with Them","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2307.13100","title":"Label Noise: Correcting the Forward-Correction","created":"2023-07-24","cited_by_count":1,"area":null},{"id":"2409.06830","title":"Noisy Early Stopping for Noisy Labels","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2501.11063","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","created":"2025-01-19","cited_by_count":1,"area":null},{"id":"2502.14281","title":"Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shifts","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2605.20347","title":"Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2101.01366","title":"A Symmetric Loss Perspective of Reliable Machine Learning","created":"2021-01-05","cited_by_count":0,"area":null},{"id":"2107.08792","title":"Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matching","created":"2021-07-08","cited_by_count":0,"area":null},{"id":"2108.01431","title":"Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2108.09154","title":"Contrastive Representations for Label Noise Require Fine-Tuning","created":"2021-08-20","cited_by_count":0,"area":null},{"id":"2110.02651","title":"Weak Novel Categories without Tears: A Survey on Weak-Shot Learning","created":"2021-10-06","cited_by_count":0,"area":null},{"id":"2205.00160","title":"Elucidating Meta-Structures of Noisy Labels in Semantic Segmentation by Deep Neural Networks","created":"2022-04-30","cited_by_count":0,"area":null},{"id":"2206.13025","title":"Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2211.07566","title":"Self-distillation with Online Diffusion on Batch Manifolds Improves Deep Metric Learning","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2302.09114","title":"Smoothly Giving up: Robustness for Simple Models","created":"2023-02-17","cited_by_count":0,"area":null},{"id":"2307.00479","title":"Domain Transfer Through Image-to-Image Translation for Uncertainty-Aware Prostate Cancer Classification","created":"2023-07-02","cited_by_count":0,"area":null},{"id":"2308.09643","title":"biquality-learn: a Python library for Biquality Learning","created":"2023-08-18","cited_by_count":0,"area":null},{"id":"2310.01109","title":"R-divergence for Estimating Model-oriented Distribution Discrepancy","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2404.04800","title":"Coordinated Sparse Recovery of Label Noise","created":"2024-04-07","cited_by_count":0,"area":null}],"next_cursor":"100"}