AI RESEARCH
Toward Robust Semi-supervised Regression via Dual-stream Knowledge Distillation
arXiv CS.LG
•
ArXi:2508.14082v3 Announce Type: replace Semi-supervised regression (SSR), which aims to predict continuous scores for samples while reducing the reliance on large-scale labeled data, has recently attracted considerable attention across various applications, including computer vision, natural language processing, audio analysis, and medical analysis. Existing SSR methods typically train models with scarce labeled data by