mlsanityData to 14 Oct 2026

Weakly Supervised AUC Optimization: A Unified Partial AUC Approach

arXiv 2305.14258 ↗First posted 23 May 2023cs.LG cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Since acquiring perfect supervision is usually difficult, real-world machine learning tasks often confront inaccurate, incomplete, or inexact supervision, collectively referred to as weak supervision. In this work, we present WSAUC, a unified framework for weakly supervised AUC optimization problems, which covers noisy label learning, positive-unlabeled learning, multi-instance learning, and semi-supervised learning scenarios. Within the WSAUC framework, we first frame the AUC optimization problems in various weakly supervised scenarios as a common formulation of minimizing the AUC risk on contaminated sets, and demonstrate that the empirical risk minimization problems are consistent with the true AUC. Then, we introduce a new type of partial AUC, specifically, the reversed partial AUC (rpAUC), which serves as a robust training objective for AUC maximization in the presence of contaminated labels. WSAUC offers a universal solution for AUC optimization in various weakly supervised scenarios by maximizing the empirical rpAUC. Theoretical and experimental results under multiple settings support the effectiveness of WSAUC on a range of weakly supervised AUC optimization tasks.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 37 of its 107 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

37 of 107 references.

References · 37

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  4. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  5. 2017A Closer Look at Memorization in Deep Networkscited by 942
  6. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  7. 2015Gated Graph Sequence Neural Networkscited by 796
  8. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  9. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  10. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  11. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  12. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
25 more
  1. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
  2. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  3. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  4. 2015Semi-Supervised Learning with Ladder Networkscited by 247
  5. 2017Positive-Unlabeled Learning with Non-Negative Risk Estimatorcited by 219
  6. 2018Learning from positive and unlabeled data: a surveycited by 219
  7. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  8. 2020Does label smoothing mitigate label noise?cited by 204
  9. 2016Multiple Instance Learning: A Survey of Problem Characteristics and Applicationscited by 164
  10. 2019Learning From Noisy Labels By Regularized Estimation Of Annotator Confusioncited by 127
  11. 2020A Survey of Label-noise Representation Learning: Past, Present and Futurecited by 122
  12. 2022AUC Maximization in the Era of Big Data and AI: A Surveycited by 100
  13. 2018Masking: A New Perspective of Noisy Supervisioncited by 93
  14. 2019Stochastic AUC Maximization with Deep Neural Networkscited by 61
  15. 2019On Symmetric Losses for Learning from Corrupted Labelscited by 53
  16. 2018On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Datacited by 43
  17. 2013One-Pass AUC Optimizationcited by 42
  18. 2022When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guaranteecited by 29
  19. 2020Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labelscited by 25
  20. 2017Semi-Supervised AUC Optimization based on Positive-Unlabeled Learningcited by 20
  21. 2020Pointwise Binary Classification with Pairwise Confidence Comparisonscited by 20
  22. 2019Stochastic Proximal AUC Maximizationcited by 14
  23. 2015Two-Way Partial AUC and Its Propertiescited by 11
  24. 2021Learning from Noisy Labels via Dynamic Loss Thresholdingcited by 6
  25. 2019Partial AUC optimization based deep speaker embeddings with class-center learning for text-independent speaker verificationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 5; 2026: 5.

11 papers.

  1. 2026ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generationcited by 2
  2. 2025Stochastic Primal-Dual Double Block-Coordinate for Two-way Partial AUC Maximizationcited by 1
  3. 2023AUC Optimization from Multiple Unlabeled Datasetscited by 0
  4. 2025Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approachcited by 0
  5. 2025Learning Robust Diffusion Models from Imprecise Supervisioncited by 0
  6. 2025Online AUC Optimization Based on Second-order Surrogate Losscited by 0
  7. 2025Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulationscited by 0
  8. 2026Graph-based Semi-Supervised Learning via Maximum Discriminationcited by 0
  9. 2026AUC Maximization from Biased Positive-unlabeled Data with Confidencecited by 0
  10. 2026Importance Weighting for Unlabeled-unlabeled Learning under Distribution Shiftcited by 0
  11. 2026Partial AUC Maximization from Positive-unlabeled Datacited by 0