Qingxia Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Qingxia Yang has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Jiaqi Lv
School of Computer Science and Engineering, Southeast University, Nanjing 211189, China
1 shared publication - Xingyu Lu
School of Computer Science and Engineering, Southeast University, Nanjing 211189, China
1 shared publication
Latest Publications
- Open Access
- 17 November 2026
- Published by MDPI AG in Electronics
- Vol. 15 (22) , 5352
Enhancing Partial-Label Learning via Structure-Aware Representation Alignment
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.
- 17 November 2026
- Published by MDPI AG in Electronics
- Vol. 15 (22) , 5352
Open AccessEnhancing Partial-Label Learning via Structure-Aware Representation Alignment
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.