VR-GNN: Variational Relation Vector Graph Neural Network for Modeling both Homophily and Heterophily

TL;DR

VR-GNN introduces a relation vector translation approach using a variational auto-encoder to effectively model both homophily and heterophily in graph neural networks, outperforming existing methods especially under heterophily.

Contribution

The paper proposes VR-GNN, a novel GNN model that employs relation vector translation with a variational auto-encoder for flexible neighbor relationship modeling.

Findings

VR-GNN outperforms state-of-the-art GNNs on heterophily datasets.

VR-GNN achieves competitive results under homophily conditions.

Extensive experiments validate the effectiveness of VR-GNN across diverse datasets.

Abstract

Graph Neural Networks (GNNs) have achieved remarkable success in diverse real-world applications. Traditional GNNs are designed based on homophily, which leads to poor performance under heterophily scenarios. Current solutions deal with heterophily mainly by mixing high-order neighbors or passing signed messages. However, mixing high-order neighbors destroys the original graph structure and passing signed messages utilizes an inflexible message-passing mechanism, which is prone to producing unsatisfactory effects. To overcome the above problems, we propose a novel GNN model based on relation vector translation named Variational Relation Vector Graph Neural Network (VR-GNN). VR-GNN models relation generation and graph aggregation into an end-to-end model based on Variational Auto-Encoder. The encoder utilizes the structure, feature and label to generate a proper relation vector. The decoder achieves superior node representation by incorporating the relation translation into the message-passing framework. VR-GNN can fully capture the homophily and heterophily between nodes due to the great flexibility of relation translation in modeling neighbor relationships. We conduct extensive experiments on eight real-world datasets with different homophily-heterophily properties to verify the effectiveness of our model. The experimental results show that VR-GNN gains consistent and significant improvements against state-of-the-art GNN methods under heterophily, and competitive performance under homophily.