# Complementary Classifier Induced Partial Label Learning

arXiv: https://arxiv.org/abs/2305.09897 · HTML: https://mlsanity.com/paper/2305.09897/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 22 references that are in the map.
- First posted on arXiv 17 May 2023.

## Builds on (most cited first, 5 of 5)

- [Learning with Biased Complementary Labels](https://mlsanity.com/paper/1711.09535/) (2017)
- [Learning from Complementary Labels](https://mlsanity.com/paper/1705.07541/) (2017)
- [Learning with Multiple Complementary Labels](https://mlsanity.com/paper/1912.12927/) (2019)
- [Partial Label Learning with Self-Guided Retraining](https://mlsanity.com/paper/1902.03045/) (2019)
- [GM-PLL: Graph Matching based Partial Label Learning](https://mlsanity.com/paper/1901.03073/) (2019)

## Built on by (most cited first, 3 of 3)

- [Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning](https://mlsanity.com/paper/2312.11034/) (2023)
- [Partial Label Clustering](https://mlsanity.com/paper/2505.03207/) (2025)
- [Why Can Accurate Models Be Learned from Inaccurate Annotations?](https://mlsanity.com/paper/2505.16159/) (2025)

## Abstract (arXiv)

In partial label learning (PLL), each training sample is associated with a set of candidate labels, among which only one is valid. The core of PLL is to disambiguate the candidate labels to get the ground-truth one. In disambiguation, the existing works usually do not fully investigate the effectiveness of the non-candidate label set (a.k.a. complementary labels), which accurately indicates a set of labels that do not belong to a sample. In this paper, we use the non-candidate labels to induce a complementary classifier, which naturally forms an adversarial relationship against the traditional PLL classifier, to eliminate the false-positive labels in the candidate label set. Besides, we assume the feature space and the label space share the same local topological structure captured by a dynamic graph, and use it to assist disambiguation. Extensive experimental results validate the superiority of the proposed approach against state-of-the-art PLL methods on 4 controlled UCI data sets and 6 real-world data sets, and reveal the usefulness of complementary learning in PLL. The code has been released in the link https://github.com/Chongjie-Si/PL-CL.