ASIAM-HGNN: Automatic Selection and Interpretable Aggregation of Meta-Path Instances for Heterogeneous Graph Neural Network

Authors

  • Xiaojun Lou Department of School of Mathematics and Computer, Zhejiang A & F University, Hangzhou 311300, China
  • Guanjun Liu Department of Computer Science, Key Laboratory of Embedded System and Service Computing, Tongji University, Shanghai 201804, China
  • Jian Li Department of School of Mathematics and Computer, Zhejiang A & F University, Hangzhou 311300, China

DOI:

https://doi.org/10.31577/cai_2023_2_257

Keywords:

Graph neural networks, meta-paths, network representation learning, heterogeneous graph

Abstract

In heterogeneous information network (HIN)-based applications, the existing methods usually use Heterogeneous Graph Neural Networks (HGNN) to handle some complex tasks. However, these methods still have some shortcomings: 1) they manually pre-select some meta-paths and thus some important ones are missing, while the missing ones still contains the information and features of the node in the entire graph structure; and 2) they have no high interpretability since they do not consider the logical sequences in an HIN. In order to deal with them, we propose ASIAM-HGNN: a heterogeneous graph neural network combined with the automatic selection and interpretable aggregation of meta-path instances. Our model can automatically filter important meta paths for each node, while preserving the logical sequence between nodes, so as to solve the problems existing in other models. A group of experiments are conducted on real-world datasets, and the results demonstrate that the models learned by our method have a better performance in most of task scenarios.

Downloads

Download data is not yet available.

Downloads

Published

2023-05-30

How to Cite

Lou, X., Liu, G., & Li, J. (2023). ASIAM-HGNN: Automatic Selection and Interpretable Aggregation of Meta-Path Instances for Heterogeneous Graph Neural Network. COMPUTING AND INFORMATICS, 42(2), 257–279. https://doi.org/10.31577/cai_2023_2_257