Link Prediction through Deep Generative Model

• Main Authors: Xu-Wen Wang, Yize Chen, Yang-Yu Liu
• Format: Article
• Language: English
• Published: Elsevier 2020-10-01
• Series: iScience
• Subjects: Complex Systems; Network Modeling; Network Topology
• Online Access: http://www.sciencedirect.com/science/article/pii/S258900422030818X

Summary: Inferring missing links based on the currently observed network is known as link prediction, which has tremendous real-world applications in biomedicine, e-commerce, social media, and criminal intelligence. Numerous methods have been proposed to solve the link prediction problem. Yet, many of these methods are designed for undirected networks only and based on domain-specific heuristics. Here we developed a new link prediction method based on deep generative models, which does not rely on any domain-specific heuristic and works for general undirected or directed complex networks. Our key idea is to represent the adjacency matrix of a network as an image and then learn hierarchical feature representations of the image by training a deep generative model. Those features correspond to structural patterns in the network at different scales, from small subgraphs to mesoscopic communities. When applied to various real-world networks from different domains, our method shows overall superior performance against existing methods.