BuffGraph: Enhancing Class-Imbalanced Node Classification via Buffer Nodes
This addresses the problem of biased predictions in Graph Neural Networks for researchers and practitioners dealing with imbalanced graph data, representing an incremental improvement over existing methods.
The paper tackles class imbalance in graph-structured data for node classification by introducing BuffGraph, which inserts buffer nodes to modulate majority class influence on minority nodes, achieving superior performance over baselines across diverse real-world datasets.
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.