SemiReward: A General Reward Model for Semi-supervised Learning

arXiv:2310.03013v2 Announce Type: replace
Abstract: Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias. However, existing pseudo-label selection strategies are limited to pre-defined schemes or complex hand-crafted policies specially designed for classification, failing to achieve high-quality labels, fast convergence, and task versatility simultaneously. To these ends, we propose a Semi-supervised Reward framework (SemiReward) that predicts reward scores to …

arxiv cs.ai cs.lg general reward model semi-supervised semi-supervised learning supervised learning type