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

TL;DR

This paper introduces GRL_EnSAT, a graph representation learning model that effectively captures structural and temporal patterns in evolving networks for improved dynamic link prediction.

Contribution

It proposes a novel model combining GAT, self-attention, and masked self-attention to learn dynamic network features, outperforming existing methods.

Findings

Outperforms most advanced baselines on four real datasets

Better captures nonlinear dynamic features of evolving networks

Achieves superior link prediction accuracy

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.