Latent neighborhood-based heterogeneous graph representation. (October 2022)

• Record Type: Journal Article
• Authors: Xiao, Yang; Quan, Pei; Lei, MingLong; Niu, Lingfeng
• Is Part Of: Neural networks. Volume 154(2022)
• Page Start: 413
• Page End: 424
• Publication Date: 2022-10
• Subjects: Heterogeneous graph -- Graph neural networks -- Graph representation learning -- Meta-path generation -- HodgeRank; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2022.07.028
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Graph, as a powerful data structure, has shown superior capability on modeling complex systems. Since real-world objects and their interactions are often multi-modal and multi-typed, compared with traditional homogeneous graphs, heterogeneous graphs can represent real-world objects more effectively. Meanwhile, rich semantic information brings great challenges for learning heterogeneous graph representation (HGR). Most existing HGR methods are based on the concept of meta-path, which is constructed based on direct neighbors and define composite semantic relations in heterogeneous graph. However, when the direct neighbor information is inadequate, which always happens due to insufficient observation, the quality of meta-paths cannot be guaranteed. Therefore, we propose a novel HGR framework based on latent direct neighbors. Specifically, random walks are first utilized to discover the potential candidates from indirect neighbors. Then HodgeRank is introduced to determine the latent direct neighbors according to their importance to the target. After that, neighborhood relationships are augmented with the selected latent direct neighbors, and the adjacency tensor of the heterogeneous graph is refactored correspondingly. Finally, Graph Transformer Network is adopted to construct semantic meta-paths automatically and generate HGR. Numerical experiments on different real-world heterogeneous networks show that our new approach can produce more meta-path instances and introduce more complex and diverse semantic information, and consequently achieves more accurate predictions compared with several state-of-the-art baselines. Highlights: We propose a novel direct neighbor set augmentation method for heterogeneous graphs. It obtains candidates by random walks & selects latent direct neighbors by HodgeRank. We augment heterogeneous graph tensor with latent direct neighborhood relationship. We design a new heterogeneous graph embedding method based on augmented tensor & GTN. Comparison experiments with several baselines show the superiority of our new method.