Imbalanced Node Classification Beyond Homophilic Assumption

TL;DR

This paper introduces GraphSANN, a novel method for imbalanced node classification that effectively handles both homophilic and heterophilic graphs by generating synthetic nodes and adaptively extracting subgraphs.

Contribution

The paper proposes a unified framework with a feature mixer, adaptive subgraph extractor, and multi-filter encoder to improve imbalanced node classification beyond homophilic assumptions.

Findings

Outperforms existing methods on eight datasets.

Effective on both homophilic and heterophilic graphs.

Demonstrates robustness to class imbalance.

Abstract

Imbalanced node classification widely exists in real-world networks where graph neural networks (GNNs) are usually highly inclined to majority classes and suffer from severe performance degradation on classifying minority class nodes. Various imbalanced node classification methods have been proposed recently which construct synthetic nodes and edges w.r.t. minority classes to balance the label and topology distribution. However, they are all based on the homophilic assumption that nodes of the same label tend to connect despite the wide existence of heterophilic edges in real-world graphs. Thus, they uniformly aggregate features from both homophilic and heterophilic neighbors and rely on feature similarity to generate synthetic edges, which cannot be applied to imbalanced graphs in high heterophily. To address this problem, we propose a novel GraphSANN for imbalanced node classification on both homophilic and heterophilic graphs. Firstly, we propose a unified feature mixer to generate synthetic nodes with both homophilic and heterophilic interpolation in a unified way. Next, by randomly sampling edges between synthetic nodes and existing nodes as candidate edges, we design an adaptive subgraph extractor to adaptively extract the contextual subgraphs of candidate edges with flexible ranges. Finally, we develop a multi-filter subgraph encoder that constructs different filter channels to discriminatively aggregate neighbor's information along the homophilic and heterophilic edges. Extensive experiments on eight datasets demonstrate the superiority of our model for imbalanced node classification on both homophilic and heterophilic graphs.