Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction.

Journal: Neural networks : the official journal of the International Neural Network Society
PMID:

Abstract

Topological structures of real-world graphs often exhibit heterogeneity involving diverse nodes and relation types. In recent years, heterogeneous graph learning methods utilizing meta-paths to capture composite relations and guide neighbor selection have garnered considerable attention. However, meta-path based approaches may establish connections between nodes of different categories while overlooking relations between nodes of the same category, decreasing the quality of node embeddings. In light of this, this paper proposes a Heterogeneous Graph Neural Network with Adaptive Relation Reconstruction (HGNN-AR) that adaptively adjusts the relations to alleviate connection deficiencies and heteromorphic issues. HGNN-AR is grounded on distinct connections derived from multiple meta-paths. By examining the homomorphic correlations of latent features from each meta-path, we reshape the cross-node connections to explore the pertinent latent relations. Through the relation reconstruction, we unveil unique connections reflected by each meta-path and incorporate them into graph convolutional networks for more comprehensive representations. The proposed model is evaluated on various benchmark heterogeneous graph datasets, demonstrating superior performance compared to state-of-the-art competitors.

Authors

  • Weihong Lin
    Department of Obstetrics and Gynecology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian 362000, P.R. China.
  • Zhaoliang Chen
    College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University, Fuzhou 350116, China. Electronic address: chenzl23@outlook.com.
  • Yuhong Chen
    Fujian Provincial Key Laboratory of Innovative Drug Target Research and State Key Laboratory of Cellular Stress Biology, School of Pharmaceutical Sciences, Xiamen University, Xiamen, 361102, China.
  • Shiping Wang
    College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong, Shenzhen 518172, China. Electronic address: shipingwangphd@163.com.