Robust Semi-Supervised Learning in Open Environments

TL;DR

This paper reviews recent advances in robust semi-supervised learning methods designed to handle inconsistent unlabeled data in open environments, emphasizing techniques for managing label, feature, and distribution discrepancies.

Contribution

It introduces recent techniques addressing data inconsistency in SSL and presents evaluation benchmarks, highlighting open research challenges.

Findings

Techniques for handling label, feature, and distribution inconsistencies in SSL.

Evaluation benchmarks for robust SSL in open environments.

Discussion of open research problems in the field.

Abstract

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.