3LPR: A three-stage label propagation and reassignment framework for class-imbalanced semi-supervised learning

Xiangyuan Kong, Xiang Wei, Xiaoyu Liu, Jingjie Wang, Siyang Lu, Weiwei Xing, Wei Lu

Abstract: Semi-supervised learning (SSL) has been studied widely in standard benchmark datasets; however, real-world data often exhibit class-imbalanced distributions, which pose significant challenges for deep semi-supervised models. To address this issue, we design a three-stage learning framework, 3LPR, by combining unsupervised feature extraction, graph-based Label Propagation, and mixed data augmentation (MDA)-based label Reassignment. Specifically, we first explore the performance of supervised and unsupervised learning for feature extraction of class-imbalanced data and then establish our first stage of feature extraction through unsupervised learning. Then, we adopt graph network-based offline label propagation and sieving to effectively expand the labeled set to overcome the excessive label bias in the classifier during the training process. Finally, we propose a label reassignment (LRA) algorithm for class-imbalanced semi-supervised learning (CISSL) to train the expanded dataset, where the MDA strategy is adopted but with the label reassigned. The experimental results demonstrate that the proposed 3LPR framework for CISSL outperforms other state-of-the-art methods on various datasets.