mlsanityData to 7 Oct 2026

Leveraged Weighted Loss for Partial Label Learning

arXiv 2106.05731 ↗First posted 10 Jun 2021cs.LGcited by 66

Not on the map. Why?

Abstract (arXiv)

As an important branch of weakly supervised learning, partial label learning deals with data where each instance is assigned with a set of candidate labels, whereas only one of them is true. Despite many methodology studies on learning from partial labels, there still lacks theoretical understandings of their risk consistent properties under relatively weak assumptions, especially on the link between theoretical results and the empirical choice of parameters. In this paper, we propose a family of loss functions named textitLeveraged Weighted (LW) loss, which for the first time introduces the leverage parameter β to consider the trade-off between losses on partial labels and non-partial ones. From the theoretical side, we derive a generalized result of risk consistency for the LW loss in learning from partial labels, based on which we provide guidance to the choice of the leverage parameter β. In experiments, we verify the theoretical guidance, and show the high effectiveness of our proposed LW loss on both benchmark and real datasets compared with other state-of-the-art partial label learning algorithms.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). Builds on 16 of its 51 references that are in the map. First posted on arXiv 10 Jun 2021.

Builds on

16 of 51 references.

References · 16

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  4. 2018Deep Learning for Classical Japanese Literaturecited by 415
  5. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  6. 2020Progressive Identification of True Labels for Partial-Label Learningcited by 102
  7. 2020Provably Consistent Partial-Label Learningcited by 92
  8. 2017Learning from Complementary Labelscited by 88
  9. 2018Complementary-Label Learning for Arbitrary Losses and Modelscited by 57
  10. 2019Learning with Multiple Complementary Labelscited by 53
  11. 2019Partial Label Learning with Self-Guided Retrainingcited by 47
  12. 2020Structured Prediction with Partial Labelling through the Infimum Losscited by 34
4 more
  1. 2017Learning from Ambiguously Labeled Face Imagescited by 29
  2. 2019GM-PLL: Graph Matching based Partial Label Learningcited by 23
  3. 2019A Regularization Approach for Instance-Based Superset Label Learningcited by 21
  4. 2020Network Cooperation with Progressive Disambiguation for Partial Label Learningcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 9; 2023: 21; 2024: 12; 2025: 15; 2026: 5.

66 papers.

Sort:

By area:

  1. 2021Instance-Dependent Partial Label Learningcited by 49
  2. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 30
  3. 2022Progressive Purification for Instance-Dependent Partial Label Learningcited by 23
  4. 2023Long-Tailed Partial Label Learning via Dynamic Rebalancingcited by 22
  5. 2021Efficient Algorithms for Learning from Coarse Labelscited by 21
  6. 2022PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learningcited by 21
  7. 2021On the Robustness of Average Losses for Partial-Label Learningcited by 20
  8. 2024Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Datacited by 19
  9. 2023On Learning Latent Models with Multi-Instance Weak Supervisioncited by 13
  10. 2023Binary Classification with Confidence Differencecited by 13
  11. 2023CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learningcited by 11
  12. 2023Towards Effective Visual Representations for Partial-Label Learningcited by 11
38 more
  1. 2025Realistic Evaluation of Deep Partial-Label Learning Algorithmscited by 11
  2. 2023Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practicalcited by 10
  3. 2022Learning with Partial Labels from Semi-supervised Perspectivecited by 9
  4. 2023ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learningcited by 9
  5. 2023Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurationscited by 9
  6. 2023Disambiguated Attention Embedding for Multi-Instance Partial-Label Learningcited by 9
  7. 2021Learning with Proper Partial Labelscited by 8
  8. 2024A General Framework for Learning from Weak Supervisioncited by 7
  9. 2024Tuning Vision-Language Models with Candidate Labels by Prompt Alignmentcited by 6
  10. 2025Multi-Instance Partial-Label Learning with Margin Adjustmentcited by 4
  11. 2022Rethinking the Learning Paradigm for Facial Expression Recognitioncited by 3
  12. 2022IRNet: Iterative Refinement Network for Noisy Partial Label Learningcited by 3
  13. 2023Unreliable Partial Label Learning with Recursive Separationcited by 3
  14. 2023Partial Label Learning for Emotion Recognition from EEGcited by 3
  15. 2023A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognitioncited by 3
  16. 2023Partial-Label Regressioncited by 3
  17. 2022Controller-Guided Partial Label Consistency Regularization with Unlabeled Datacited by 2
  18. 2023Towards Unbiased Exploration in Partial Label Learningcited by 2
  19. 2023Robust Representation Learning for Unreliable Partial Label Learningcited by 2
  20. 2024Exploiting Conjugate Label Information for Multi-Instance Partial-Label Learningcited by 2
  21. 2025An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noisecited by 2
  22. 2025Tuning the Right Foundation Models is What you Need for Partial Label Learningcited by 2
  23. 2023Exploiting Counter-Examples for Active Learning with Partial labelscited by 1
  24. 2024Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learningcited by 1
  25. 2025Weakly-Supervised Contrastive Learning for Imprecise Class Labelscited by 1
  26. 2025Learning from Interval Targetscited by 1
  27. 2022Decompositional Generation Process for Instance-Dependent Partial Label Learningcited by 0
  28. 2022Meta Objective Guided Disambiguation for Partial Label Learningcited by 0
  29. 2023Learning from Stochastic Labelscited by 0
  30. 2023Pseudo Labels Regularization for Imbalanced Partial-Label Learningcited by 0
  31. 2023Adversary-Aware Partial label learning with Label distillationcited by 0
  32. 2023Q&A Label Learningcited by 0
  33. 2023Partial-label Learning with Mixed Closed-set and Open-set Out-of-candidate Examplescited by 0
  34. 2024MIMIC: Mask Image Pre-training with Mix Contrastive Fine-tuning for Facial Expression Recognitioncited by 0
  35. 2024Partial Label Learning with Focal Loss for Sea Ice Classification Based on Ice Chartscited by 0
  36. 2024Pre-Trained Vision-Language Models as Partial Annotatorscited by 0
  37. 2024AsyCo: An Asymmetric Dual-task Co-training Model for Partial-label Learningcited by 0
  38. 2024An Unbiased Risk Estimator for Partial Label Learning with Augmented Classescited by 0

50 most cited of 66 All 66 (JSON)