Link Prediction via Ranking Metric Dual-Level Attention Network Learning

Link prediction is a challenging problem for complex network analysis, arising in many disciplines such as social networks and telecommunication networks. Currently, many existing approaches estimate the proximity of the link endpoints from the local neighborhood around them for link prediction, which suffer from the localized view of network connections. In this paper, we consider the problem of link prediction from the viewpoint of learning path-based proximity ranking metric embedding. We propose a novel proximity ranking metric attention network learning framework by jointly exploiting both node-level and path-level attention proximity of the endpoints to their betweenness paths for learning the discriminative feature representation for link prediction. We then develop the path-based dual-level attentional learning method with multi-step reasoning process for proximity ranking metric embedding. The extensive experiments on two large-scale datasets show that our method achieves better performance than other state-of-the-art solutions to the problem.