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

TL;DR

This paper introduces R-GSN, a novel relation-based graph neural network that improves performance on large-scale heterogeneous graphs without relying on meta-paths, simplifying the process and enhancing scalability.

Contribution

The paper proposes a new message passing paradigm and R-GSN model that eliminates the need for meta-paths in heterogeneous graph neural networks.

Findings

Achieves state-of-the-art performance on ogbn-mag dataset

Outperforms baseline R-GCN significantly

Simplifies heterogeneous graph learning process

Abstract

Heterogeneous graph is a kind of data structure widely existing in real life. Nowadays, the research of graph neural network on heterogeneous graph 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.