期刊
INTELLIGENT DATA ANALYSIS
卷 26, 期 1, 页码 173-188出版社
IOS PRESS
DOI: 10.3233/IDA-205524
关键词
Directed network; temporal link prediction; graph neural network; autoencoder; self-attention mechanism
资金
- Foundation for Innovative Research Groups of the National Natural Science Foundation of China [61521003]
- National Natural Science Foundation of China [61803384]
This paper investigates the properties of directed and temporal networks and proposes a deep learning model, TSAM, based on GCN and self-attention mechanism, to address the problem of temporal link prediction in directed networks. Experimental results show that TSAM outperforms most benchmarks under two evaluation metrics.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据