Knowledge graph embedding with shared latent semantic units

doi:10.1016/j.neunet.2021.02.013

	Knowledge graph embedding with shared latent semantic units
	Zhang, Zhao 3,4; Zhuang, Fuzhen 3,4; Qu, Meng 2; Niu, Zheng-Yu 1; Xiong, Hui 2; He, Qing 3,4
刊名	NEURAL NETWORKS
	2021-07-01
卷号	139 页码:140-148
关键词	Knowledge graph Reinforcement learning Embedding
ISSN号	0893-6080
DOI	10.1016/j.neunet.2021.02.013
英文摘要	Knowledge graph embedding (KGE) aims to project both entities and relations into a continuous low-dimensional space. However, for a given knowledge graph (KG), only a small number of entities and relations occur many times, while the vast majority of entities and relations occur less frequently. This data sparsity problem has largely been ignored by most of the existing KGE models. To this end, in this paper, we propose a general technique to enable knowledge transfer among semantically similar entities or relations. Specifically, we define latent semantic units (LSUs), which are the sub-components of entity and relation embeddings. Semantically similar entities or relations are supposed to share the same LSUs, and thus knowledge can be transferred among entities or relations. Finally, extensive experiments show that the proposed technique is able to enhance existing KGE models and can provide better representations of KGs. (C) 2021 Elsevier Ltd. All rights reserved.
资助项目	National Key Research and Development Program of China[2017YFB1002104] ; National Natural Science Foundation of China[U1836206] ; National Natural Science Foundation of China[U1811461] ; National Natural Science Foundation of China[61773361] ; Project of Youth Innovation Promotion Association CAS, China[2017146]
WOS研究方向	Computer Science ; Neurosciences & Neurology
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:000652750100011
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17717]
专题	中国科学院计算技术研究所
通讯作者	Zhuang, Fuzhen
作者单位	1.Baidu Inc, Beijing, Peoples R China 2.Rutgers State Univ, Management Sci & Informat Syst, New Brunswick, NJ USA 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Zhao,Zhuang, Fuzhen,Qu, Meng,et al. Knowledge graph embedding with shared latent semantic units[J]. NEURAL NETWORKS,2021,139:140-148.
APA	Zhang, Zhao,Zhuang, Fuzhen,Qu, Meng,Niu, Zheng-Yu,Xiong, Hui,&He, Qing.(2021).Knowledge graph embedding with shared latent semantic units.NEURAL NETWORKS,139,140-148.
MLA	Zhang, Zhao,et al."Knowledge graph embedding with shared latent semantic units".NEURAL NETWORKS 139(2021):140-148.