Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition

TL;DR

This paper proposes a novel theoretical framework combining bias-variance decomposition with graph augmentation to improve imbalanced node classification in GNNs, demonstrating superior performance over existing methods.

Contribution

It introduces a new bias-variance based approach for imbalanced GNN node classification, integrating graph augmentation and regularization to reduce variance impact.

Findings

Outperforms state-of-the-art methods on multiple benchmarks

Effectively handles naturally and artificially imbalanced datasets

Provides a new theoretical perspective on class imbalance in GNNs

Abstract

This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data. Our approach integrates imbalanced node classification and Bias-Variance Decomposition, establishing a theoretical framework that closely relates data imbalance to model variance. We also leverage graph augmentation technique to estimate the variance, and design a regularization term to alleviate the impact of imbalance. Exhaustive tests are conducted on multiple benchmarks, including naturally imbalanced datasets and public-split class-imbalanced datasets, demonstrating that our approach outperforms state-of-the-art methods in various imbalanced scenarios. This work provides a novel theoretical perspective for addressing the problem of imbalanced node classification in GNNs.