mlsanityData to 7 Oct 2026

Provably Consistent Partial-Label Learning

arXiv 2007.08929 ↗First posted 17 Jul 2020cs.LG stat.MLcited by 92

Not on the map. Why?

Abstract (arXiv)

Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels. Even though many practical PLL methods have been proposed in the last two decades, there lacks a theoretical understanding of the consistency of those methods-none of the PLL methods hitherto possesses a generation process of candidate label sets, and then it is still unclear why such a method works on a specific dataset and when it may fail given a different dataset. In this paper, we propose the first generation model of candidate label sets, and develop two novel PLL methods that are guaranteed to be provably consistent, i.e., one is risk-consistent and the other is classifier-consistent. Our methods are advantageous, since they are compatible with any deep network or stochastic optimizer. Furthermore, thanks to the generation model, we would be able to answer the two questions above by testing if the generation model matches given candidate label sets. Experiments on benchmark and real-world datasets validate the effectiveness of the proposed generation model and two PLL methods.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 12; 2023: 25; 2024: 20; 2025: 18; 2026: 7.

92 papers.

Sort:

By area:

  1. 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
  2. 2021Leveraged Weighted Loss for Partial Label Learningcited by 66
  3. 2021Instance-Dependent Partial Label Learningcited by 49
  4. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 30
  5. 2022Progressive Purification for Instance-Dependent Partial Label Learningcited by 23
  6. 2022One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancementcited by 22
  7. 2023Long-Tailed Partial Label Learning via Dynamic Rebalancingcited by 22
  8. 2021Efficient Algorithms for Learning from Coarse Labelscited by 21
  9. 2022PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learningcited by 21
  10. 2021On the Robustness of Average Losses for Partial-Label Learningcited by 20
  11. 2021Learning from Similarity-Confidence Datacited by 19
  12. 2024Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Datacited by 19
38 more
  1. 2021Learning from Multiple Noisy Partial Labelerscited by 14
  2. 2021Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classificationcited by 12
  3. 2023CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learningcited by 11
  4. 2023Towards Effective Visual Representations for Partial-Label Learningcited by 11
  5. 2025Realistic Evaluation of Deep Partial-Label Learning Algorithmscited by 11
  6. 2023Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practicalcited by 10
  7. 2024Hyper Evidential Deep Learning to Quantify Composite Classification Uncertaintycited by 10
  8. 2022Learning with Partial Labels from Semi-supervised Perspectivecited by 9
  9. 2023ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learningcited by 9
  10. 2023Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurationscited by 9
  11. 2023Disambiguated Attention Embedding for Multi-Instance Partial-Label Learningcited by 9
  12. 2023Active Learning for Semantic Segmentation with Multi-class Label Querycited by 9
  13. 2021Learning with Proper Partial Labelscited by 8
  14. 2023Learning From Biased Soft Labelscited by 8
  15. 2024A General Framework for Learning from Weak Supervisioncited by 7
  16. 2024Mixed Blessing: Class-Wise Embedding guided Instance-Dependent Partial Label Learningcited by 7
  17. 2023Weakly Supervised Regression with Interval Targetscited by 6
  18. 2023Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guaranteescited by 6
  19. 2024Tuning Vision-Language Models with Candidate Labels by Prompt Alignmentcited by 6
  20. 2023A Universal Unbiased Method for Classification from Aggregate Observationscited by 5
  21. 2023Unified Risk Analysis for Weakly Supervised Learningcited by 5
  22. 2025Multi-Instance Partial-Label Learning with Margin Adjustmentcited by 4
  23. 2021Multi-Class Classification from Single-Class Data with Confidencescited by 3
  24. 2022Rethinking the Learning Paradigm for Facial Expression Recognitioncited by 3
  25. 2022IRNet: Iterative Refinement Network for Noisy Partial Label Learningcited by 3
  26. 2023Unreliable Partial Label Learning with Recursive Separationcited by 3
  27. 2023A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognitioncited by 3
  28. 2023Partial-Label Regressioncited by 3
  29. 2024Partial-Label Learning with a Reject Optioncited by 3
  30. 2022Learning from Label Proportions with Instance-wise Consistencycited by 2
  31. 2022Controller-Guided Partial Label Consistency Regularization with Unlabeled Datacited by 2
  32. 2023Towards Unbiased Exploration in Partial Label Learningcited by 2
  33. 2023Robust Representation Learning for Unreliable Partial Label Learningcited by 2
  34. 2024Learning from Reduced Labels for Long-Tailed Datacited by 2
  35. 2024Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategiescited by 2
  36. 2024Exploiting Conjugate Label Information for Multi-Instance Partial-Label Learningcited by 2
  37. 2025Partial-Label Learning with Conformal Candidate Cleaningcited by 2
  38. 2025Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMscited by 2

50 most cited of 92 All 92 (JSON)