# Provably Consistent Partial-Label Learning

arXiv: https://arxiv.org/abs/2007.08929 · HTML: https://mlsanity.com/paper/2007.08929/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 30 of 92)

- [To Smooth or Not? When Label Smoothing Meets Noisy Labels](https://mlsanity.com/paper/2106.04149/) (2021)
- [Leveraged Weighted Loss for Partial Label Learning](https://mlsanity.com/paper/2106.05731/) (2021)
- [Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2110.12911/) (2021)
- [SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning](https://mlsanity.com/paper/2209.10365/) (2022)
- [Progressive Purification for Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2206.00830/) (2022)
- [One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement](https://mlsanity.com/paper/2206.00517/) (2022)
- [Long-Tailed Partial Label Learning via Dynamic Rebalancing](https://mlsanity.com/paper/2302.05080/) (2023)
- [Efficient Algorithms for Learning from Coarse Labels](https://mlsanity.com/paper/2108.09805/) (2021)
- [PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning](https://mlsanity.com/paper/2201.08984/) (2022)
- [On the Robustness of Average Losses for Partial-Label Learning](https://mlsanity.com/paper/2106.06152/) (2021)
- [Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data](https://mlsanity.com/paper/2406.10502/) (2024)
- [Learning from Similarity-Confidence Data](https://mlsanity.com/paper/2102.06879/) (2021)
- [Learning from Multiple Noisy Partial Labelers](https://mlsanity.com/paper/2106.04530/) (2021)
- [Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification](https://mlsanity.com/paper/2102.00678/) (2021)
- [Realistic Evaluation of Deep Partial-Label Learning Algorithms](https://mlsanity.com/paper/2502.10184/) (2025)
- [CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning](https://mlsanity.com/paper/2303.10365/) (2023)
- [Towards Effective Visual Representations for Partial-Label Learning](https://mlsanity.com/paper/2305.06080/) (2023)
- [Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty](https://mlsanity.com/paper/2404.10980/) (2024)
- [Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning](https://mlsanity.com/paper/2305.16912/) (2023)
- [Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical](https://mlsanity.com/paper/2311.15502/) (2023)
- [Learning with Partial Labels from Semi-supervised Perspective](https://mlsanity.com/paper/2211.13655/) (2022)
- [ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning](https://mlsanity.com/paper/2301.12077/) (2023)
- [Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations](https://mlsanity.com/paper/2305.12715/) (2023)
- [Active Learning for Semantic Segmentation with Multi-class Label Query](https://mlsanity.com/paper/2309.09319/) (2023)
- [Learning with Proper Partial Labels](https://mlsanity.com/paper/2112.12303/) (2021)
- [Learning From Biased Soft Labels](https://mlsanity.com/paper/2302.08155/) (2023)
- [A General Framework for Learning from Weak Supervision](https://mlsanity.com/paper/2402.01922/) (2024)
- [Mixed Blessing: Class-Wise Embedding guided Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2412.05029/) (2024)
- [Weakly Supervised Regression with Interval Targets](https://mlsanity.com/paper/2306.10458/) (2023)
- [Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees](https://mlsanity.com/paper/2308.10487/) (2023)

## 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.