Collaborative Dual Representations for Semi-Supervised Partial Label Learning

Wei-Xuan Bao; Yong Rui; Min-Ling Zhang

AAAI 2026technical0 citations

Collaborative Dual Representations for Semi-Supervised Partial Label Learning

Abstract

Semi-supervised partial label learning (SSPLL) aims to improve the generalization performance of partial label (PL) classifiers by effectively leveraging unlabeled data. Nevertheless, the inherent ambiguity in supervision, where the ground-truth label of a PL example is hidden within a set of candidate labels, poses significant challenges. The presence of false positive labels potentially misleads model

BibTeX

@inproceedings{aaai2026_collaborativedua,
  title = {Collaborative Dual Representations for Semi-Supervised Partial Label Learning},
  author = {Wei-Xuan Bao and Yong Rui and Min-Ling Zhang},
  booktitle = {AAAI 2026},
  year = {2026}
}