ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning

TL;DR

This paper introduces ABC, a novel auxiliary balanced classifier designed to improve semi-supervised learning on imbalanced datasets by combining class-balanced training with existing SSL methods, leading to state-of-the-art results.

Contribution

The paper proposes a scalable class-imbalanced SSL algorithm that integrates an auxiliary balanced classifier with existing SSL models, effectively handling class imbalance in unlabeled data.

Findings

Achieves state-of-the-art performance on imbalanced SSL benchmarks.

Effectively mitigates class bias in semi-supervised learning.

Utilizes a novel class-balanced loss with consistency regularization.

Abstract

Existing semi-supervised learning (SSL) algorithms typically assume class-balanced datasets, although the class distributions of many real-world datasets are imbalanced. In general, classifiers trained on a class-imbalanced dataset are biased toward the majority classes. This issue becomes more problematic for SSL algorithms because they utilize the biased prediction of unlabeled data for training. However, traditional class-imbalanced learning techniques, which are designed for labeled data, cannot be readily combined with SSL algorithms. We propose a scalable class-imbalanced SSL algorithm that can effectively use unlabeled data, while mitigating class imbalance by introducing an auxiliary balanced classifier (ABC) of a single layer, which is attached to a representation layer of an existing SSL algorithm. The ABC is trained with a class-balanced loss of a minibatch, while using high-quality representations learned from all data points in the minibatch using the backbone SSL algorithm to avoid overfitting and information loss.Moreover, we use consistency regularization, a recent SSL technique for utilizing unlabeled data in a modified way, to train the ABC to be balanced among the classes by selecting unlabeled data with the same probability for each class. The proposed algorithm achieves state-of-the-art performance in various class-imbalanced SSL experiments using four benchmark datasets.