Dynamic Link Prediction Using Graph Representation Learning with Enhanced Structure and Temporal Information

Abstract

The links in many real networks are evolving with time. The task of dynamic link prediction is to use past connection histories to infer links of the network at a future time. How to effectively learn the temporal and structural pattern of the network dynamics is the key. In this paper, we propose a graph representation learning model based on enhanced structure and temporal information (GRL_EnSAT). For structural information, we exploit a combination of a graph attention network (GAT) and a self-attention network to capture structural neighborhood. For temporal dynamics, we use a masked self-attention network to capture the dynamics in the link evolution. In this way, GRL_EnSAT not only learns low-dimensional embedding vectors but also preserves the nonlinear dynamic feature of the evolving network. GRL_EnSAT is evaluated on four real datasets, in which GRL_EnSAT outperforms most advanced baselines. Benefiting from the dynamic self-attention mechanism, GRL_EnSAT yields better performance than approaches based on recursive graph evolution modeling.