Label-Wise Graph Convolutional Network for Heterophilic Graphs

TL;DR

This paper introduces a label-wise graph convolutional network that effectively handles both homophilic and heterophilic graphs by avoiding dissimilar node aggregation and using bi-level optimization for model selection.

Contribution

It proposes a novel label-wise message passing mechanism and a bi-level optimization approach to improve GNN performance on diverse graph types.

Findings

Effective on both homophilic and heterophilic graphs

Outperforms existing GNNs in node classification tasks

Theoretically justified framework

Abstract

Graph Neural Networks (GNNs) have achieved remarkable performance in modeling graphs for various applications. However, most existing GNNs assume the graphs exhibit strong homophily in node labels, i.e., nodes with similar labels are connected in the graphs. They fail to generalize to heterophilic graphs where linked nodes may have dissimilar labels and attributes. Therefore, in this paper, we investigate a novel framework that performs well on graphs with either homophily or heterophily. More specifically, we propose a label-wise message passing mechanism to avoid the negative effects caused by aggregating dissimilar node representations and preserve the heterophilic contexts for representation learning. We further propose a bi-level optimization method to automatically select the model for graphs with homophily/heterophily. Theoretical analysis and extensive experiments demonstrate the effectiveness of our proposed framework for node classification on both homophilic and heterophilic graphs.