《计算机应用研究》|Application Research of Computers

基于时序模体注意力图卷积的动态网络链路预测算法

Dynamic link prediction algorithm based on graph convolutional networks via temporal motif-based attention

免费全文下载 (已被下载 次)  
获取PDF全文
作者 吴铮,陈鸿昶,张建朋
机构 战略支援部队信息工程大学 信息技术研究所,郑州 450003
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2021)10-046-3143-05
DOI 10.19734/j.issn.1001-3695.2021.01.0029
摘要 时序网络中的动态链路预测旨在基于历史连边信息预测未来会产生的连边,是网络分析的重要组成部分,具有极大的理论研究价值和广阔的应用场景。针对现有的动态链路预测算法大多基于一阶连边关系预测未来连边,忽略了对高阶的拓扑信息和时序通联信息的挖掘和利用问题,提出一种基于时序模体注意力图卷积的动态链路预测算法。首先,提出一种时序模体邻接矩阵构建算法,利用时序模体抽取节点间的高阶拓扑和时序关系信息;然后利用隐式调节过程对网络演化过程进行建模,并使用时序模体邻接矩阵作为传输矩阵的图卷积神经网络学习节点的低维向量表示并进行迭代更新;最后以节点间表示向量作为输入,通过计算连边发生的条件密度函数值作为依据完成动态链路预测。在多个真实时序网络数据集上的实验结果表明,所提算法可有效挖掘节点间的高阶拓扑和时序信息,提高动态链路预测效果。
关键词 时序模体; 图卷积; 动态链路预测
基金项目 国家自然基金青年基金项目
郑州市协同创新重大专项
中国博士后科学基金面上项目
本文URL http://www.arocmag.com/article/01-2021-10-046.html
英文标题 Dynamic link prediction algorithm based on graph convolutional networks via temporal motif-based attention
作者英文名 Wu Zheng, Chen Hongchang, Zhang Jianpeng
机构英文名 Institute of Information Technology,PLA Strategic Support Force Information Engineering University,Zhengzhou 450003,China
英文摘要 Aiming to predict edges in the future based on historical linkage status, dynamic link prediction in temporal networks is an important component of the network analysis and has great value in theoretical research and wide applications. Concerning the problem that current dynamic link prediction algorithms mostly only consider first-order relations to infer future links, while ignoring exploiting the higher-order topological and temporal relationships among nodes, this paper proposed a dynamic link prediction algorithm based on graph convolutional network via temporal motif-based attention. Firstly, it designed a temporal motif-based adjacency matrix construction algorithm, exploiting the higher-order topological and temporal relationships among nodes. Then it modeled the evolution of temporal network with latent mediation process, while iteratively updated the low-dimensional node representations with temporal motif-based adjacency matrix as the transmission matrix in graph convolutional network. Finally, it predicted the future links based on the conditional intensity function with node representations as input. Experimental results on various real-world temporal network datasets show that the proposed algorithm can effectively mine the high-order topological and temporal information among nodes, and improve the performance of the dynamic link prediction.
英文关键词 temporal motif; graph convolutional network; dynamic link prediction
参考文献 查看稿件参考文献
 
收稿日期 2021/1/10
修回日期 2021/3/2
页码 3143-3147
中图分类号 TP181
文献标志码 A