Node-dependent Semantic Search over Heterogeneous Graph Neural Networks

Zhenyi Wang, Huan Zhao, Fengqi Liang, Chuan Shi

Abstract: In recent years, Heterogeneous Graph Neural Networks (HGNNs) have been the state-of-the-art approaches for various tasks on Heterogeneous Graphs (HGs), e.g., recommendation and social network analysis. Despite the success of existing HGNNs, the utilization of the intricate semantic information in HGs is still insufficient. In this work, we study the problem of how to design powerful HGNNs under the guidance of node-dependent semantics. Specifically, to perform semantic search over HGNNs, we propose to develop semantic structures in terms of relation selection and connection selection, which could guide a task-relevant message flow. Furthermore, to better capture the diversified property of different node samples in HGs, we design predictors to adaptively decide the semantic structures per node. Extensive experiments on seven benchmarking datasets across different downstream tasks, i.e., node classification and recommendation, show that our method can consistently outperform various state-of-the-art baselines with shorter inference latency, which justifies its effectiveness and efficiency. The code and data are available at https://github.com/BUPT-GAMMA/NDS.