Partial Label Learning with a Partner

Authors

  • Chongjie Si Shanghai Jiao Tong University
  • Zekun Jiang Shanghai Jiao Tong University
  • Xuehui Wang Shanghai Jiao Tong University
  • Yan Wang East China Normal University
  • Xiaokang Yang Shanghai Jiao Tong University
  • Wei Shen Shanghai Jiao Tong University

DOI:

https://doi.org/10.1609/aaai.v38i13.29424

Keywords:

ML: Classification and Regression, ML: Multi-class/Multi-label Learning & Extreme Classification

Abstract

In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth. The majority of the existing works focuses on constructing robust classifiers to estimate the labeling confidence of candidate labels in order to identify the correct one. However, these methods usually struggle to rectify mislabeled samples. To help existing PLL methods identify and rectify mislabeled samples, in this paper, we introduce a novel partner classifier and propose a novel ``mutual supervision'' paradigm. Specifically, we instantiate the partner classifier predicated on the implicit fact that non-candidate labels of a sample should not be assigned to it, which is inherently accurate and has not been fully investigated in PLL. Furthermore, a novel collaborative term is formulated to link the base classifier and the partner one. During each stage of mutual supervision, both classifiers will blur each other's predictions through a blurring mechanism to prevent overconfidence in a specific label. Extensive experiments demonstrate that the performance and disambiguation ability of several well-established stand-alone and deep-learning based PLL approaches can be significantly improved by coupling with this learning paradigm.

Published

2024-03-24

How to Cite

Si, C., Jiang, Z., Wang, X., Wang, Y., Yang, X., & Shen, W. (2024). Partial Label Learning with a Partner. Proceedings of the AAAI Conference on Artificial Intelligence, 38(13), 15029-15037. https://doi.org/10.1609/aaai.v38i13.29424

Issue

Section

AAAI Technical Track on Machine Learning IV