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.

6 pages,3 figures, 3 tables, Published at the CSCWD conference

References in corpus (6)

• Graph Embedding Techniques, Applications, and Performance: A Survey
• struc2vec: Learning Node Representations from Structural Identity
• Motifs in Temporal Networks
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
• Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space
• CoarSAS2hvec: Heterogeneous Information Network Embedding with Balanced Network Sampling