MIRROR: Mining Implicit Relationships via Structure-Enhanced Graph Convolutional Networks

• Main Authors: LIU, Jiaying, XIA, Feng, REN, Jing, XU, Bo, PANG, Guansong, CHI, Lianhua
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Relation mining; implicit relationships; graph convolutional networks; heterogeneous networks; Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8002; https://ink.library.smu.edu.sg/context/sis_research/article/9005/viewcontent/Mirror_pv.pdf
• Institution: Singapore Management University

Data explosion in the information society drives people to develop more effective ways to extract meaningful information. Extracting semantic information and relational information has emerged as a key mining primitive in a wide variety of practical applications. Existing research on relation mining has primarily focused on explicit connections and ignored underlying information, e.g., the latent entity relations. Exploring such information (defined as implicit relationships in this article) provides an opportunity to reveal connotative knowledge and potential rules. In this article, we propose a novel research topic, i.e., how to identify implicit relationships across heterogeneous networks. Specially, we first give a clear and generic definition of implicit relationships. Then, we formalize the problem and propose an efficient solution, namely MIRROR, a graph convolutional network (GCN) model to infer implicit ties under explicit connections. MIRROR captures rich information in learning node-level representations by incorporating attributes from heterogeneous neighbors. Furthermore, MIRROR is tolerant of missing node attribute information because it is able to utilize network structure. We empirically evaluate MIRROR on four different genres of networks, achieving state-of-the-art performance for target relations mining. The underlying information revealed by MIRROR contributes to enriching existing knowledge and leading to novel domain insights.