中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Matching Knowledge Graphs in Entity Embedding Spaces: An Experimental Study

文献类型：期刊论文

作者Zeng, Weixin3; Zhao, Xiang3; Tan, Zhen2; Tang, Jiuyang3; Cheng, Xueqi1
刊名IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
出版日期2023-12-01
卷号35期号:12页码:12770-12784
关键词Entity alignment entity matching knowledge graph knowledge graph alignment
ISSN号1041-4347
DOI10.1109/TKDE.2023.3272584
英文摘要Entity alignment (EA) identifies equivalent entities that locate in different knowledge graphs (KGs), and has attracted growing research interests over the last few years with the advancement of KG embedding techniques. Although a pile of embedding-based EA frameworks have been developed, they mainly focus on improving the performance of entity representation learning, while largely overlook the subsequent stage that matches KGs in entity embedding spaces. Nevertheless, accurately matching entities based on learned entity representations is crucial to the overall alignment performance, as it coordinates individual alignment decisions and determines the global matching result. Hence, it is essential to understand how well existing solutions for matching KGs in entity embedding spaces perform on present benchmarks, as well as their strengths and weaknesses. To this end, in this article we provide a comprehensive survey and evaluation of matching algorithms for KGs in entity embedding spaces in terms of effectiveness and efficiency on both classic settings and new scenarios that better mirror real-life challenges. Based on in-depth analysis, we provide useful insights into the design trade-offs and good paradigms of existing works, and suggest promising directions for future development.
资助项目National Key R&D Program of China[2020AAA0108800] ; NSFC[62272469] ; NSFC[71971212]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001105152100016
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/38810]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhao, Xiang
作者单位1.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China
2.Natl Univ Def Technol, Sci & Technol Informat Syst Engn Lab, Changsha 410073, Hunan, Peoples R China
3.Natl Univ Def Technol, Lab Big Data & Decis, Changsha 410073, Hunan, Peoples R China
推荐引用方式
GB/T 7714		 Zeng, Weixin,Zhao, Xiang,Tan, Zhen,et al. Matching Knowledge Graphs in Entity Embedding Spaces: An Experimental Study[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2023,35(12):12770-12784.
APA Zeng, Weixin,Zhao, Xiang,Tan, Zhen,Tang, Jiuyang,&Cheng, Xueqi.(2023).Matching Knowledge Graphs in Entity Embedding Spaces: An Experimental Study.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,35(12),12770-12784.
MLA Zeng, Weixin,et al."Matching Knowledge Graphs in Entity Embedding Spaces: An Experimental Study".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 35.12(2023):12770-12784.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。