Class-Imbalanced Semi-Supervised Learning

2020/02/17 by Minsung Hyun, Hyun, Minsung, Jisoo Jeong +3 · 37 citations
Computer Science · Health Professions · Mathematics · Medicine · #Artificial Intelligence in Healthcare #Artificial intelligence #COVID-19 diagnosis using AI #Class (philosophy) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #FOS: Computer and information sciences #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #cs.CV #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.2002.06815

published in arXiv (Cornell University) (Cornell University) · 16 pages

arxiv created 2020/02/17 · openalex publication_date 2020/02/17 · arxiv updated 2020/02/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Wide Residual Networks
• SGDR: Stochastic Gradient Descent with Warm Restarts
• mixup: Beyond Empirical Risk Minimization
• A systematic study of the class imbalance problem in convolutional neural networks
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• Temporal Ensembling for Semi-Supervised Learning
• Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Semi-Supervised Supply Chain Fraud Detection with Unsupervised Pre-Filtering
• BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition
• CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

Related

• An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning
• ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning
• CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
• SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples
• Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning