Determined Multi-Label Learning via Similarity-Based Prompt

arXiv:2403.16482v1 Announce Type: new
Abstract: In multi-label classification, each training instance is associated with multiple class labels simultaneously. Unfortunately, collecting the fully precise class labels for each training instance is time- and labor-consuming for real-world applications. To alleviate this problem, a novel labeling setting termed \textit{Determined Multi-Label Learning} (DMLL) is proposed, aiming to effectively alleviate the labeling cost inherent in multi-label tasks. In this novel labeling setting, each training instance is associated with a \textit{determined label} (either "Yes" or "No"), …

abstract applications arxiv class classification cs.lg instance labeling labels labor multiple novel prompt training type via world