Robust Semi-Supervised Learning in Open Environments
It tackles the practical issue of robust SSL for real-world applications where data inconsistencies are common, but it is incremental as it reviews existing research rather than proposing new methods.
This paper addresses the problem of semi-supervised learning in open environments where inconsistencies between labeled and unlabeled data cause severe performance degradation, and it reviews advances and benchmarks for handling label, feature, and distribution inconsistencies.
Semi-supervised learning (SSL) aims to improve performance by exploiting unlabeled data when labels are scarce. Conventional SSL studies typically assume close environments where important factors (e.g., label, feature, distribution) between labeled and unlabeled data are consistent. However, more practical tasks involve open environments where important factors between labeled and unlabeled data are inconsistent. It has been reported that exploiting inconsistent unlabeled data causes severe performance degradation, even worse than the simple supervised learning baseline. Manually verifying the quality of unlabeled data is not desirable, therefore, it is important to study robust SSL with inconsistent unlabeled data in open environments. This paper briefly introduces some advances in this line of research, focusing on techniques concerning label, feature, and data distribution inconsistency in SSL, and presents the evaluation benchmarks. Open research problems are also discussed for reference purposes.