Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embedding

TL;DR

This paper introduces RE-GNN, a simple framework that enhances homogeneous GNNs to effectively process heterogeneous graphs by using relation embeddings and a gradient scaling approach.

Contribution

The paper proposes a novel relation embedding method for homogeneous GNNs to handle heterogeneity, with a gradient scaling technique for optimization, improving expressiveness and efficiency.

Findings

RE-GNN outperforms existing methods on heterogeneous graph tasks.

RE-GNN is compatible with various homogeneous GNN architectures.

Theoretical analysis shows RE-GNN has greater expressive power than GTN.

Abstract

Graph Neural Networks (GNNs) have been generalized to process the heterogeneous graphs by various approaches. Unfortunately, these approaches usually model the heterogeneity via various complicated modules. This paper aims to propose a simple yet effective framework to assign adequate ability to the homogeneous GNNs to handle the heterogeneous graphs. Specifically, we propose Relation Embedding based Graph Neural Network (RE-GNN), which employs only one parameter per relation to embed the importance of distinct types of relations and node-type-specific self-loop connections. To optimize these relation embeddings and the model parameters simultaneously, a gradient scaling factor is proposed to constrain the embeddings to converge to suitable values. Besides, we interpret the proposed RE-GNN from two perspectives, and theoretically demonstrate that our RE-GCN possesses more expressive power than GTN (which is a typical heterogeneous GNN, and it can generate meta-paths adaptively). Extensive experiments demonstrate that our RE-GNN can effectively and efficiently handle the heterogeneous graphs and can be applied to various homogeneous GNNs.