BuffGraph: Enhancing Class-Imbalanced Node Classification via Buffer Nodes

TL;DR

BuffGraph introduces buffer nodes into graphs to mitigate majority class bias, significantly improving minority class classification in imbalanced graph datasets through extensive empirical validation.

Contribution

This paper proposes BuffGraph, a novel method that inserts buffer nodes to reduce majority class influence and enhance minority class representation in class-imbalanced node classification.

Findings

BuffGraph outperforms baseline methods on real-world datasets.

Buffer nodes effectively reduce bias from majority classes.

Method is validated in both natural and artificially imbalanced settings.

Abstract

Class imbalance in graph-structured data, where minor classes are significantly underrepresented, poses a critical challenge for Graph Neural Networks (GNNs). To address this challenge, existing studies generally generate new minority nodes and edges connecting new nodes to the original graph to make classes balanced. However, they do not solve the problem that majority classes still propagate information to minority nodes by edges in the original graph which introduces bias towards majority classes. To address this, we introduce BuffGraph, which inserts buffer nodes into the graph, modulating the impact of majority classes to improve minor class representation. Our extensive experiments across diverse real-world datasets empirically demonstrate that BuffGraph outperforms existing baseline methods in class-imbalanced node classification in both natural settings and imbalanced settings. Code is available at https://anonymous.4open.science/r/BuffGraph-730A.