TSAM: Temporal Link Prediction in Directed Networks based on Self-Attention Mechanism

Abstract

The development of graph neural networks (GCN) makes it possible to learn structural features from evolving complex networks. Even though a wide range of realistic networks are directed ones, few existing works investigated the properties of directed and temporal networks. In this paper, we address the problem of temporal link prediction in directed networks and propose a deep learning model based on GCN and self-attention mechanism, namely TSAM. The proposed model adopts an autoencoder architecture, which utilizes graph attentional layers to capture the structural feature of neighborhood nodes, as well as a set of graph convolutional layers to capture motif features. A graph recurrent unit layer with self-attention is utilized to learn temporal variations in the snapshot sequence. We run comparative experiments on four realistic networks to validate the effectiveness of TSAM. Experimental results show that TSAM outperforms most benchmarks under two evaluation metrics.

References in corpus (10)

• Link Prediction in Complex Networks: A Survey
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
• DynGEM: Deep Embedding Method for Dynamic Graphs
• Scalable Link Prediction in Dynamic Networks via Non-Negative Matrix Factorization
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
• Local structure of directed networks
• GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction
• Link Prediction via Graph Attention Network
• motif2vec: Motif Aware Node Representation Learning for Heterogeneous Networks
• Which way? Direction-Aware Attributed Graph Embedding