GraphMSE: Efficient Meta-path Selection in Semantically Aligned Feature Space for Graph Neural Networks

Authors

  • Yi Li Peking University, Beijing, China
  • Yilun Jin The Hong Kong University of Science and Technology, Hong Kong SAR, China
  • Guojie Song Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China
  • Zihao Zhu Beijing University of Posts and Telecommunications, Beijing, China
  • Chuan Shi Beijing University of Posts and Telecommunications, Beijing, China
  • Yiming Wang Peking University, Beijing, China

Keywords:

Graph Mining, Social Network Analysis & Community

Abstract

Heterogeneous information networks (HINs) are ideal for describing real-world data with different types of entities and relationships. To carry out machine learning on HINs, meta-paths are widely utilized to extract semantics with pre-defined patterns, and models such as graph convolutional networks (GCNs) are thus enabled. However, previous works generally assume a fixed set of meta-paths, which is unrealistic as real-world data are overwhelmingly diverse. Therefore, it is appealing if meta-paths can be automatically selected given an HIN, yet existing works aiming at such problem possess drawbacks, such as poor efficiency and ignoring feature heterogeneity. To address these drawbacks, we propose GraphMSE, an efficient heterogeneous GCN combined with automatic meta-path selection. Specifically, we design highly efficient meta-path sampling techniques, and then injectively project sampled meta-path instances to vectors. We then design a novel semantic feature space alignment, aiming to align the meta-path instance vectors and hence facilitate meta-path selection. Extensive experiments on real-world datasets demonstrate that GraphMSE outperforms state-of-the-art counterparts, figures out important meta-paths, and is dramatically (e.g. 200 times) more efficient.

Downloads

Published

2021-05-18

How to Cite

Li, Y., Jin, Y., Song, G., Zhu, Z., Shi, C., & Wang, Y. (2021). GraphMSE: Efficient Meta-path Selection in Semantically Aligned Feature Space for Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4206-4214. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16544

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management