Block Modeling-Guided Graph Convolutional Neural Networks

TL;DR

This paper introduces a novel GCN framework that incorporates block modeling to enable effective aggregation in both homophilic and heterophilic networks, improving performance on diverse real-world graph data.

Contribution

It proposes a block modeling-guided GCN that automatically learns aggregation rules for neighbors of different classes, addressing heterophily in graph neural networks.

Findings

Outperforms state-of-the-art methods on heterophilic datasets.

Maintains competitive performance on homophilic datasets.

Enables discriminative aggregation based on neighbor homophily degree.

Abstract

Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation. However, the GCN aggregating mechanism fails to generalize to networks with heterophily where most nodes have neighbors from different classes, which commonly exists in real-world networks. In order to make the propagation and aggregation mechanism of GCN suitable for both homophily and heterophily (or even their mixture), we introduce block modeling into the framework of GCN so that it can realize "block-guided classified aggregation", and automatically learn the corresponding aggregation rules for neighbors of different classes. By incorporating block modeling into the aggregation process, GCN is able to aggregate information from homophilic and heterophilic neighbors discriminately according to their homophily degree. We compared our algorithm with state-of-art methods which deal with the heterophily problem. Empirical results demonstrate the superiority of our new approach over existing methods in heterophilic datasets while maintaining a competitive performance in homophilic datasets.