Contrastive Credibility Propagation for Reliable Semi-Supervised Learning

arXiv:2211.09929v4 Announce Type: replace
Abstract: Producing labels for unlabeled data is error-prone, making semi-supervised learning (SSL) troublesome. Often, little is known about when and why an algorithm fails to outperform a supervised baseline. Using benchmark datasets, we craft five common real-world SSL data scenarios: few-label, open-set, noisy-label, and class distribution imbalance/misalignment in the labeled and unlabeled sets. We propose a novel algorithm called Contrastive Credibility Propagation (CCP) for deep SSL via iterative transductive pseudo-label refinement. CCP unifies semi-supervised learning and …

abstract algorithm arxiv benchmark class craft cs.lg data datasets distribution error five labels making propagation semi-supervised semi-supervised learning set ssl supervised learning type world