HiWalk: Learning node embeddings from heterogeneous networks. (March 2019)

• Record Type: Journal Article
• Authors: Bai, Jie; Li, Linjing; Zeng, Daniel
• Is Part Of: Information systems. Volume 81(2019)
• Page Start: 82
• Page End: 91
• Publication Date: 2019-03
• Subjects: Network analysis -- Representation learning -- Behavioral analysis -- Random walk -- Heterogeneous network; Database management -- Periodicals; Electronic data processing -- Periodicals; Bases de données -- Gestion -- Périodiques; Informatique -- Périodiques; Database management; Electronic data processing; Periodicals; 005.7
• DOI: 10.1016/j.is.2018.11.008
• Languages: English
• ISSNs: 0306-4379

Abstract

Abstract: Heterogeneous networks, such as bibliographical networks and online business networks, are ubiquitous in everyday life. Nevertheless, analyzing them for high-level semantic understanding still poses a great challenge for modern information systems. In this paper, we propose HiWalk to learn distributed vector representations of the nodes in heterogeneous networks. HiWalk is inspired by the state-of-the-art representation learning algorithms employed in the context of both homogeneous networks and heterogeneous networks, based on word embedding learning models. Different from existing methods in the literature, the purpose of HiWalk is to learn vector representations of the targeted set of nodes by leveraging the other nodes as "background knowledge", which maximizes the structural correlations of contiguous nodes. HiWalk decomposes the adjacent probabilities of the nodes and adopts a hierarchical random walk strategy, which makes it more effective, efficient and concentrated when applied to practical large-scale heterogeneous networks. HiWalk can be widely applied in heterogeneous networks environments to analyze targeted types of nodes. We further validate the effectiveness of the proposed HiWalk through multiple tasks conducted on two real-world datasets. Highlights: A method of learning embeddings for given type of nodes in heterogeneous networks. A hierarchical method, leveraging the other part of nodes as "background knowledge". More effective, efficient and concentrated in heterogeneous network learning. It can be applied to many real-world analysis tasks.