EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Enhancing Partial-Label Learning via Structure-Aware Representation Alignment

Jiaqi Lv, Qingxia Yang, Xingyu Lu

Electronics · 2026-11-17 · 15 (22) · 5352

DOI: 10.3390/electronics15225352 ↗

At a glance

Journal article in Electronics, published online on 2026-11-17. Written by Jiaqi Lv and 2 co-authors. 31 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, Jiangsu Natural Science Foundation, Fundamental Research Funds for the Central Universities.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Partial-label learning aims to learn from ambiguous supervision, where each instance is annotated with a set of candidate labels that contain only one correct class. While recent advances rely on local discriminative objectives to enhance representation quality, they often overlook the global structure of the representation space, leading to greater relative dispersion in inter-class representation differences, which may impair generalization. In this work, we propose RDAP (Representation Difference Alignment for Partial-Label Learning), a structure-aware regularization framework that regularizes the relative dispersion of inter-class representation differences using predicted label distributions, without requiring ground-truth labels. RDAP introduces a novel alignment loss guided by distribution-level dissimilarity between predicted labels, combined with stochastic representation masking to reduce computational cost. RDAP is fully compatible with existing PLL pipelines and can be seamlessly integrated without architectural modifications. Extensive experiments across diverse datasets and candidate-label protocols show that RDAP can enhance structural representation quality and achieve competitive classification performance across a range of partial-label learning benchmarks.

Funding

  • National Natural Science Foundation of China
  • Jiangsu Natural Science Foundation
  • Fundamental Research Funds for the Central Universities
  • Big Data Computing Center of Southeast University

Cite

APA

Lv, J., Yang, Q., & Lu, X. (2026). Enhancing Partial-Label Learning via Structure-Aware Representation Alignment. Electronics, 15(22), 5352. https://doi.org/10.3390/electronics15225352

Vancouver

Lv J, Yang Q, Lu X. Enhancing Partial-Label Learning via Structure-Aware Representation Alignment. Electronics. 2026;15(22):5352. doi:10.3390/electronics15225352

BibTeX
@article{Lv2026,
  author = {Lv, Jiaqi and Yang, Qingxia and Lu, Xingyu},
  title = {Enhancing Partial-Label Learning via Structure-Aware Representation Alignment},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {22},
  pages = {5352},
  doi = {10.3390/electronics15225352}
}
Start for free →