# Exploiting the Potential Supervision Information of Clean Samples in Partial Label Learning

arXiv: https://arxiv.org/abs/2505.09354 · HTML: https://mlsanity.com/paper/2505.09354/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 14 May 2025.

## Builds on (most cited first, 18 of 18)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Progressive Identification of True Labels for Partial-Label Learning](https://mlsanity.com/paper/2002.08053/) (2020)
- [Provably Consistent Partial-Label Learning](https://mlsanity.com/paper/2007.08929/) (2020)
- [Leveraged Weighted Loss for Partial Label Learning](https://mlsanity.com/paper/2106.05731/) (2021)
- [Detecting Corrupted Labels Without Training a Model to Predict](https://mlsanity.com/paper/2110.06283/) (2021)
- [Variational Positive-incentive Noise: How Noise Benefits Models](https://mlsanity.com/paper/2306.07651/) (2023)
- [SIMPLE: A Gradient Estimator for k-Subset Sampling](https://mlsanity.com/paper/2210.01941/) (2022)
- [SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning](https://mlsanity.com/paper/2209.10365/) (2022)
- [GM-PLL: Graph Matching based Partial Label Learning](https://mlsanity.com/paper/1901.03073/) (2019)
- [Progressive Purification for Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2206.00830/) (2022)
- [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)
- [Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical](https://mlsanity.com/paper/2311.15502/) (2023)
- [ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning](https://mlsanity.com/paper/2301.12077/) (2023)
- [A Unified Approach to Count-Based Weakly-Supervised Learning](https://mlsanity.com/paper/2311.13718/) (2023)
- [Mixed Blessing: Class-Wise Embedding guided Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2412.05029/) (2024)
- [A Self-paced Regularization Framework for Partial-Label Learning](https://mlsanity.com/paper/1804.07759/) (2018)

## Abstract (arXiv)

Diminishing the impact of false-positive labels is critical for conducting disambiguation in partial label learning. However, the existing disambiguation strategies mainly focus on exploiting the characteristics of individual partial label instances while neglecting the strong supervision information of clean samples randomly lying in the datasets. In this work, we show that clean samples can be collected to offer guidance and enhance the confidence of the most possible candidates. Motivated by the manner of the differentiable count loss strat- egy and the K-Nearest-Neighbor algorithm, we proposed a new calibration strategy called CleanSE. Specifically, we attribute the most reliable candidates with higher significance under the assumption that for each clean sample, if its label is one of the candidates of its nearest neighbor in the representation space, it is more likely to be the ground truth of its neighbor. Moreover, clean samples offer help in characterizing the sample distributions by restricting the label counts of each label to a specific interval. Extensive experiments on 3 synthetic benchmarks and 5 real-world PLL datasets showed this calibration strategy can be applied to most of the state-of-the-art PLL methods as well as enhance their performance.