R-GSN: The Relation-based Graph Similar Network for Heterogeneous Graph

Xinliang Wu, Guizhong Liu, Mengying Jiang

Keywords: Heterogeneous graph, graph neural network.

Abstract: Heterogeneous graph is a kind of data structure widely existing in real life. Nowadays, the research of graph neural networks on heterogeneous graphs has become more and more popular. The existing heterogeneous graph neural network algorithms mainly have two ideas, one is based on meta-path and the other is not. The idea based on meta-path often requires a lot of manual preprocessing, at the same time it is difficult to extend to large-scale graphs. In this paper, we proposed the general heterogeneous message passing paradigm and designed R-GSN that does not need meta-path, which is much improved compared to the baseline R-GCN. Experiments have shown that our R-GSN algorithm achieves the state-of-the-art performance on the ogbn-mag large-scale heterogeneous graph dataset.

One-sentence Summary: This paper defines a general heterogeneous message passing paradigm, under which we can design different heterogeneous graph neural network models.