Tucker decomposition-based temporal knowledge graph completion

doi:10.1016/j.knosys.2021.107841

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 智能交互

	Tucker decomposition-based temporal knowledge graph completion
	Shao, Pengpeng 2; Zhang, Dawei 2; Yang, Guohua 2; Tao, Jianhua 1,2,3; Che, Feihu 2; Liu, Tong 2
刊名	KNOWLEDGE-BASED SYSTEMS
	2022-02-28
卷号	238 页码:9
关键词	Temporal knowledge graphs Tucker decomposition Reconstruction Contrastive learning
ISSN号	0950-7051
DOI	10.1016/j.knosys.2021.107841
通讯作者	Tao, Jianhua(jhtao@nlpr.ia.ac.cn)
英文摘要	Knowledge graphs have been demonstrated to be an effective tool for numerous intelligent applications. However, a large amount of valuable knowledge still exists implicitly in the knowledge graphs. To enrich the existing knowledge graphs, recent years have witnessed that many algorithms for link prediction and knowledge graphs embedding have been designed to infer new facts. But most of these studies focus on the static knowledge graphs and ignore the temporal information which reflects the validity of knowledge. Developing the model for temporal knowledge graphs completion is an increasingly important task. In this paper, we build a new tensor decomposition model for temporal knowledge graphs completion inspired by the Tucker decomposition of order-4 tensor. Furthermore, to further improve the basic model performance, we provide three kinds of methods including cosine similarity, contrastive learning, and reconstruction-based to incorporate the prior knowledge into the proposed model. Because the core tensor contains a large number of parameters on the proposed model, thus we present two embedding regularization schemes to avoid the over-fitting problem. By combining these two kinds of regularization with the proposed model, our model outperforms baselines with an explicit margin on three temporal datasets (i.e. ICEWS2014, ICEWS05-15, GDELT).& nbsp;(c) 2021 Published by Elsevier B.V.
资助项目	National Key Research & Development Plan of China[2017YFC0820602] ; National Natural Science Foundation of China (NSFC)[61831022] ; National Natural Science Foundation of China (NSFC)[61771472] ; National Natural Science Foundation of China (NSFC)[61773379] ; National Natural Science Foundation of China (NSFC)[61901473]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000779180700014
资助机构	National Key Research & Development Plan of China ; National Natural Science Foundation of China (NSFC)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48252]
专题	模式识别国家重点实验室_智能交互
通讯作者	Tao, Jianhua
作者单位	1.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Shao, Pengpeng,Zhang, Dawei,Yang, Guohua,et al. Tucker decomposition-based temporal knowledge graph completion[J]. KNOWLEDGE-BASED SYSTEMS,2022,238:9.
APA	Shao, Pengpeng,Zhang, Dawei,Yang, Guohua,Tao, Jianhua,Che, Feihu,&Liu, Tong.(2022).Tucker decomposition-based temporal knowledge graph completion.KNOWLEDGE-BASED SYSTEMS,238,9.
MLA	Shao, Pengpeng,et al."Tucker decomposition-based temporal knowledge graph completion".KNOWLEDGE-BASED SYSTEMS 238(2022):9.