Partial Label Learning via Conditional-Label-Aware Disambiguation

• Published in: Journal of computer science and technology Vol. 36; no. 3; pp. 590 - 605
• Main Authors: Ni, Peng, Zhao, Su-Yun, Dai, Zhi-Gang, Chen, Hong, Li, Cui-Ping
• Format: Journal Article
• Language: English
• Published: Singapore Springer Singapore 01.06.2021; Springer; Springer Nature B.V; Key Laboratory of Data Engineering and Knowledge Engineering (Renmin University of China),Ministry of Education Beijing 100087,China%School of Information,Renmin University of China,Beijing 100087,China
• Subjects: Artificial Intelligence; Computer Science; Constraint modelling; Data mining; Data Structures and Information Theory; Information Systems Applications (incl.Internet); Labeling; Labels; Regular Paper; Similarity; Software Engineering; Supervised learning; Theory of Computation; similarity and dissimilarity; disambiguation; partial label learning; weak supervision
• ISSN: 1000-9000; 1860-4749
• DOI: 10.1007/s11390-021-0992-x

Partial label learning is a weakly supervised learning framework in which each instance is associated with multiple candidate labels, among which only one is the ground-truth label. This paper proposes a unified formulation that employs proper label constraints for training models while simultaneously performing pseudo-labeling. Unlike existing partial label learning approaches that only leverage similarities in the feature space without utilizing label constraints, our pseudo-labeling process leverages similarities and differences in the feature space using the same candidate label constraints and then disambiguates noise labels. Extensive experiments on artificial and real-world partial label datasets show that our approach significantly outperforms state-of-the-art counterparts on classification prediction.