ECGN: A Cluster-Aware Approach to Graph Neural Networks for Imbalanced Classification

TL;DR

ECGN is a novel graph neural network approach that leverages clustering and synthetic minority node generation to improve classification performance on imbalanced graph datasets.

Contribution

ECGN introduces cluster-specific training and synthetic minority node generation, addressing class imbalance and clustering structure simultaneously in GNNs.

Findings

ECGN outperforms existing methods by up to 11% on benchmark datasets.

The approach effectively handles class imbalance in graph node classification.

ECGN is compatible with any GNN and cluster generation technique.

Abstract

Classifying nodes in a graph is a common problem. The ideal classifier must adapt to any imbalances in the class distribution. It must also use information in the clustering structure of real-world graphs. Existing Graph Neural Networks (GNNs) have not addressed both problems together. We propose the Enhanced Cluster-aware Graph Network (ECGN), a novel method that addresses these issues by integrating cluster-specific training with synthetic node generation. Unlike traditional GNNs that apply the same node update process for all nodes, ECGN learns different aggregations for different clusters. We also use the clusters to generate new minority-class nodes in a way that helps clarify the inter-class decision boundary. By combining cluster-aware embeddings with a global integration step, ECGN enhances the quality of the resulting node embeddings. Our method works with any underlying GNN and any cluster generation technique. Experimental results show that ECGN consistently outperforms its closest competitors by up to 11% on some widely studied benchmark datasets.