SE-GRU: Structure Embedded Gated Recurrent Unit Neural Networks for Temporal Link Prediction

doi:10.1109/TNSE.2022.3164659

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 人工智能与机器学习（杨雪冰）-技术团队

	SE-GRU: Structure Embedded Gated Recurrent Unit Neural Networks for Temporal Link Prediction
	Yin, Yanting 1; Wu, Yajing2 ; Yang, Xuebing2 ; Zhang, Wensheng2,3 ; Yuan, Xiaojie 1
发表期刊	IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
ISSN	2327-4697
	2022-07-01
卷号	9 期号:4 页码:2495-2509
通讯作者	Yang, Xuebing(yangxuebing2013@ia.ac.cn) ; Yuan, Xiaojie(yuanxj@nankai.edu.cn)
摘要	Temporal link prediction on dynamic graphs is essential to various areas such as recommendation systems, social networks, and citation analysis, and thus attracts great attention in both research and industry fields. For complex graphs in real-world applications, although recent temporal link prediction methods perform well in predicting high-frequency and nearby connections, it becomes more challenging when considering low-frequency and earlier connections. In this work, we introduce a novel and elegant prediction architecture called Structure Embedded Gated Recurrent Unit (SE-GRU) neural networks, to strengthen the prediction robustness against frequency variation and occurrence delay of connections. The established SE-GRU embeds the structure for local topological characteristics to emphasize the different connection frequencies between nodes and captures the temporal dependencies to avoid losing valuable information caused by long-term changes. We realize neural network optimization considering three terms concerning reconstruction, structure, and evolution. The extensive experiments performed on three public datasets demonstrate the significant superiority of SE-GRU compared with 5 representative and state-of-the-art competitors under three evaluation metrics. The results validate the effectiveness and robustness of our proposed method, by showing that the frequencies and timestamps of connections have a little-to-no negative impact on prediction accuracy.
关键词	Time-frequency analysis Feature extraction Predictive models Optimization Topology Measurement Logic gates Temporal link prediction dynamic graphs graph embedding neural networks
DOI	10.1109/TNSE.2022.3164659
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018AAA0102100] ; National Natural Science Foundation of China[U1936206] ; National Natural Science Foundation of China[61906190] ; National Natural Science Foundation of China[61906191] ; National Natural Science Foundation of China[62077031]
项目资助者	National Key R&D Program of China ; National Natural Science Foundation of China
WOS研究方向	Engineering ; Mathematics
WOS类目	Engineering, Multidisciplinary ; Mathematics, Interdisciplinary Applications
WOS记录号	WOS:000818899600043
出版者	IEEE COMPUTER SOC
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/49156
专题	多模态人工智能系统全国重点实验室_人工智能与机器学习（杨雪冰）-技术团队
通讯作者	Yang, Xuebing; Yuan, Xiaojie
作者单位	1.Nankai Univ, Coll Comp Sci, Tianjin Key Lab Network & Data Secur Technol, Tianjin 300350, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Nankai Univ, Coll Comp Sci, Tianjin 300350, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yin, Yanting,Wu, Yajing,Yang, Xuebing,et al. SE-GRU: Structure Embedded Gated Recurrent Unit Neural Networks for Temporal Link Prediction[J]. IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING,2022,9(4):2495-2509.
APA	Yin, Yanting,Wu, Yajing,Yang, Xuebing,Zhang, Wensheng,&Yuan, Xiaojie.(2022).SE-GRU: Structure Embedded Gated Recurrent Unit Neural Networks for Temporal Link Prediction.IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING,9(4),2495-2509.
MLA	Yin, Yanting,et al."SE-GRU: Structure Embedded Gated Recurrent Unit Neural Networks for Temporal Link Prediction".IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 9.4(2022):2495-2509.