Class-Imbalanced Semi-Supervised Learning

TL;DR

This paper introduces a new semi-supervised learning setting with class imbalance, analyzes existing methods under these conditions, and proposes a robust regularization technique that improves performance in imbalanced scenarios.

Contribution

The paper defines class-imbalanced semi-supervised learning, analyzes existing SSL methods in this context, and proposes Suppressed Consistency Loss to enhance robustness against class imbalance.

Findings

SCL outperforms conventional SSL methods in imbalanced environments.

Performance improves as class imbalance severity increases.

Smaller labeled datasets benefit more from SCL.

Abstract

Semi-Supervised Learning (SSL) has achieved great success in overcoming the difficulties of labeling and making full use of unlabeled data. However, SSL has a limited assumption that the numbers of samples in different classes are balanced, and many SSL algorithms show lower performance for the datasets with the imbalanced class distribution. In this paper, we introduce a task of class-imbalanced semi-supervised learning (CISSL), which refers to semi-supervised learning with class-imbalanced data. In doing so, we consider class imbalance in both labeled and unlabeled sets. First, we analyze existing SSL methods in imbalanced environments and examine how the class imbalance affects SSL methods. Then we propose Suppressed Consistency Loss (SCL), a regularization method robust to class imbalance. Our method shows better performance than the conventional methods in the CISSL environment. In particular, the more severe the class imbalance and the smaller the size of the labeled data, the better our method performs.