FairMatch : Promoting Partial Label Learning by Unlabeled Samples

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationKDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery (ACM)
Pages1269-1278
Number of pages10
ISBN (electronic)979-8-4007-0490-1
Publication statusPublished - Aug 2024

Conference

Title30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024)
LocationCentre de Convencions Internacional de Barcelona
PlaceSpain
CityBarcelona
Period25 - 29 August 2024

Abstract

This paper studies the semi-supervised partial label learning (SSPLL) problem, which aims to improve the partial label learning (PLL) by leveraging unlabeled samples. Both the existing SSPLL methods and the semi-supervised learning methods exploit the information in unlabeled samples by selecting high-confidence unlabeled samples as the pseudo labels based on the maximum value of the model output. However, the scarcity of labeled samples and the ambiguity from partial labels skew this strategy towards an unfair selection of high-confidence samples on each class, most notably during the initial phases of training, resulting in slower training and performance degradation. In this paper, we propose a novel method FairMatch, which adopts a learning state aware self-adaptive threshold for selecting the same number of high-confidence samples on each class, and uses augmentation consistency to incorporate the unlabeled samples to promote PLL. In addition, we adopt the candidate label disambiguation to utilize the partial labeled samples and mix up the partial labeled samples and the selected high-confidence unlabeled samples to prevent the model from overfitting on partial label samples. FairMatch can achieve maximum accuracy improvements of 9.53%, 4.9%, and 16.45% onCIFAR-10, CIFAR-100, andCIFAR-100H,respectively. The codes can be found at https://github.com/jhjiangSEU/FairMatch. ©2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

Research Area(s)

  • Partial Label Learning, Semi-supervised Learning, Fair Selection

Citation Format(s)

FairMatch: Promoting Partial Label Learning by Unlabeled Samples. / Jiang, Jiahao; Jia, Yuheng; LIU, Hui et al.
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM), 2024. p. 1269-1278.

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review