A Novel Maximum Mean Discrepancy-Based Semi-Supervised Learning Algorithm

• Published in: Mathematics (Basel) Vol. 10; no. 1; p. 39
• Main Authors: Huang, Qihang, He, Yulin, Huang, Zhexue
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2022
• Subjects: Active learning; Algorithms; Classification; Classifiers; Cluster analysis; Clustering; co-training; Confidence; Datasets; distribution consistency; Machine learning; maximum mean discrepancy; Methods; Multilayer perceptrons; Paradigms; self-training; Semi-supervised learning; Statistical analysis; Statistical methods; Subject specialists; Training; Vector quantization

To provide more external knowledge for training self-supervised learning (SSL) algorithms, this paper proposes a maximum mean discrepancy-based SSL (MMD-SSL) algorithm, which trains a well-performing classifier by iteratively refining the classifier using highly confident unlabeled samples. The MMD-...