Link prediction on latent heterogeneous graphs

• Main Authors: NGUYEN, Trung Kien, LIU, Zemin, FANG, Yuan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Latent heterogeneous graph; Link prediction; Graph neural networks; Databases and Information Systems; OS and Networks
• Online Access: https://ink.library.smu.edu.sg/sis_research/8190; https://ink.library.smu.edu.sg/context/sis_research/article/9193/viewcontent/3543507.3583284_pvoa_cc_by.pdf
• Institution: Singapore Management University

On graph data, the multitude of node or edge types gives rise to heterogeneous information networks (HINs). To preserve the heterogeneous semantics on HINs, the rich node/edge types become a cornerstone of HIN representation learning. However, in real-world scenarios, type information is often noisy, missing or inaccessible. Assuming no type information is given, we define a so-called latent heterogeneous graph (LHG), which carries latent heterogeneous semantics as the node/edge types cannot be observed. In this paper, we study the challenging and unexplored problem of link prediction on an LHG. As existing approaches depend heavily on type-based information, they are suboptimal or even inapplicable on LHGs. To address the absence of type information, we propose a model named LHGNN, based on the novel idea of semantic embedding at node and path levels, to capture latent semantics on and between nodes. We further design a personalization function to modulate the heterogeneous contexts conditioned on their latent semantics w.r.t. the target node, to enable finer-grained aggregation. Finally, we conduct extensive experiments on four benchmark datasets, and demonstrate the superior performance of LHGNN.