UPL: Uncertainty-aware Pseudo-labeling for Imbalance Transductive Node Classification
This addresses class imbalance in graph node classification, which is a domain-specific problem, with incremental improvements to existing pseudo-labeling approaches.
The paper tackles class imbalance in graph-structured datasets for node classification by proposing Uncertainty-aware Pseudo-labeling (UPL), which uses pseudo-labels and uncertainty reduction to improve accuracy, achieving superior performance over state-of-the-art methods on benchmark datasets.
Graph-structured datasets often suffer from class imbalance, which complicates node classification tasks. In this work, we address this issue by first providing an upper bound on population risk for imbalanced transductive node classification. We then propose a simple and novel algorithm, Uncertainty-aware Pseudo-labeling (UPL). Our approach leverages pseudo-labels assigned to unlabeled nodes to mitigate the adverse effects of imbalance on classification accuracy. Furthermore, the UPL algorithm enhances the accuracy of pseudo-labeling by reducing training noise of pseudo-labels through a novel uncertainty-aware approach. We comprehensively evaluate the UPL algorithm across various benchmark datasets, demonstrating its superior performance compared to existing state-of-the-art methods.