R-GSN: The Relation-based Graph Similar Network for Heterogeneous Graph
This addresses scalability and manual effort issues in heterogeneous graph analysis, though it appears incremental as it builds on existing paradigms like R-GCN.
The paper tackles the problem of heterogeneous graph neural networks by proposing R-GSN, a method that avoids meta-path preprocessing and scales better, achieving state-of-the-art performance on the ogbn-mag dataset.
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.