Revisiting self-supervised contrastive learning for imbalanced classification
Open Access
- 1 April 2025
- journal article
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15 (2) , 1949-1960
Abstract
Class imbalance remains a formidable challenge in machine learning, particularly affecting fields that depend on accurate classification across skewed datasets, such as medical imaging and software defect prediction. Traditional approaches often fail to adequately address the underrepresentation of minority classes, leading to models that exhibit high performance on majority classes but have poor performance on critical minority classes. Self-supervised contrastive learning has become an extremely encouraging method for this issue, enabling the utilization of unlabeled data to generate robust and generalizable models. This paper reviews the advancements in self-supervised contrastive learning for imbalanced classification, focusing on methodologies that enhance model performance through innovative contrastive loss functions and data augmentation strategies. By pulling similar instances closer and pushing dissimilar ones apart, these techniques help mitigate the biases inherent in imbalanced datasets. We critically analyze the effectiveness of these methods in diverse scenarios and propose future research directions aimed at refining these approaches for broader application in real-world settings. This review serves as a guide for researchers exploring the potential of contrastive learning to address class imbalances, highlighting recent successes and identifying crucial gaps that need addressing.Keywords
This publication has 66 references indexed in Scilit:
- Exploring Contrastive Learning for Long-Tailed Multi-label Text Classification2024
- DisCo: Remedying Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning2022
- Few-Shot Classification with Contrastive Learning2022
- ProCo: Prototype-Aware Contrastive Learning for Long-Tailed Medical Image Classification2022
- Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images2021
- Fighting Class Imbalance with Contrastive Learning2021
- Contrastive Multiview Coding2020
- Ensemble learning: A surveyWIREs Data Mining and Knowledge Discovery, 2018
- Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning2005
- SMOTEBoost: Improving Prediction of the Minority Class in Boosting2003