Class-Imbalanced Semi-Supervised Learning

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.

16 pages

References in corpus (2)

• Temporal Ensembling for Semi-Supervised Learning
• Learning with Pseudo-Ensembles

Cited by in corpus (5)

• Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
• Multitask Learning for Class-Imbalanced Discourse Classification
• Semi-supervised learning for medical image classification using imbalanced training data
• A Semi-Supervised Framework for Misinformation Detection
• BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition