Open access
Sep 2026
Confidence-Aware Relation Contrastive Learning for Partial Multi-Label Learning
This paper formulate PML pretraining as a relation disambiguation problem and proposes a confidence-aware relation contrastive learning framework, which improves subset accuracy and F1-oriented measures under moderate and severe partial-label noise.
Shen-Huan Lyu, Ning Chen, Can Jiao et al.
· Electronics · 0 citations