Article(id=1242139551838315106, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1242139531168789435, articleNumber=null, orderNo=17, doi=10.3981/j.issn.1000-7857.2021.22.011, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1615564800000, receivedDateStr=2021-03-13, revisedDate=1627488000000, revisedDateStr=2021-07-29, acceptedDate=null, acceptedDateStr=null, onlineDate=1640062157947, onlineDateStr=2021-12-21, pubDate=1638028800000, pubDateStr=2021-11-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1640062157947, onlineIssueDateStr=2021-12-21, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774078746992, creator=sys-migrate, updateTime=1774078746992, updator=sys-migrate, issue=Issue{id=1242139531168789435, tenantId=1146029695717560320, journalId=1146031591421210625, year='2021', volume='39', issue='22', pageStart='0', pageEnd='144', issueExtLink='null', onlineDate='null', pubDate='1638028800000', pubDateStr='2021-11-28', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=3, issueType=-1, specialIssue=null, createTime=1774078742063, creator='sys-migrate', updateTime=1774078742063, updator='sys-migrate', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=94, endPage=110, ext={EN=ArticleExt(id=1242139556011647619, articleId=1242139551838315106, tenantId=1146029695717560320, journalId=1146031591421210625, language=EN, title=Knowledge graph representation learning method system in the era of artificial intelligence, columnId=1150494644690366681, journalTitle=Science & Technology Review, columnName=Papers, runingTitle=null, highlight=null, articleAbstract=In recent years, the knowledge graph representation learning has been used to represent the components of the knowledge graphs in a low-dimensional vector embedding, as a mainstream way to combine the artificial intelligence with the knowledge graphs. This paper reviews the mainstream knowledge graph representation learning methods without auxiliary information, mainly, the distance-based and the semantic matching-based methods, and the knowledge graph representation learning methods containing textual auxiliary information and category auxiliary information, along with the advantages and the disadvantages of various representation learning methods. It is found that the introduction of auxiliary information can effectively represent new entities and relationships in the knowledge graph, but the time and space costs are significantly increased, and thus the methods without auxiliary information are more easily applied in practical scenarios at this stage. Finally, we show how the knowledge graph embedding can be applied to downstream tasks such as the triad classification, the link prediction and the recommender systems. A collection of datasets and open source libraries for different tasks is compiled and, and a comprehensive outlook on promising research directions such as large-scale, dynamic knowledge graphs is given., authors=ZHANG Hui1 , YANG Weijie2,3 , LIU Wenwen1 , ZHANG Xun1,3 , DUAN Dagao3,4 , HAN Zhongming3,4 , authorsList=ZHANG Hui, YANG Weijie, LIU Wenwen, ZHANG Xun, DUAN Dagao, HAN Zhongming, authorCompany=1. School of Computer Science and Engineering, Beijing Technology and Business University, Beijing 100048, China;1 , 杨伟杰2,3 , 刘文文1 , 张珣1,3 , 段大高3,4 , 韩忠明3,4 , authorsList=张翙, 杨伟杰, 刘文文, 张珣, 段大高, 韩忠明, authorCompany=1. 北京工商大学计算机学院, 北京 100048;
科技导报
| 研究论文 2021, 39(22): 94-110
人工智能时代知识图谱表示学习方法体系
全屏
张翙1 , 杨伟杰2,3 , 刘文文1 , 张珣1,3 , 段大高3,4 , 韩忠明3,4
作者信息
1. 北京工商大学计算机学院, 北京 100048;
通讯作者:
杨伟杰(通信作者),讲师,研究方向为大数据分析与信息检索,电子信箱:yangwj@btbu.edu.cn
Knowledge graph representation learning method system in the era of artificial intelligence
Affiliations
出版时间: 2021-11-28
doi: 10.3981/j.issn.1000-7857.2021.22.011
文章导航
总结了不含辅助信息的知识图谱表示学习方法，主要是基于距离和基于语义匹配2类主流方法；研究了包含文本辅助信息和类别辅助信息的知识图谱表示学习方法；通过对比各类表示学习方法的优缺点，发现引入辅助信息能有效表达知识图谱中新实体，但时空开支大幅上升，因而在现阶段，不含辅助信息的方法更易应用于实际场景中。分析了知识图谱嵌入如何应用于三元组分类、链路预测、推荐系统等下游任务，整理归纳了应用于不同任务的数据集和开源库的集合，并展望了大规模、动态知识图谱等具有广泛应用前景的研究方向。
知识图谱
/
知识图谱嵌入
/
表示学习
/
深度学习
In recent years, the knowledge graph representation learning has been used to represent the components of the knowledge graphs in a low-dimensional vector embedding, as a mainstream way to combine the artificial intelligence with the knowledge graphs. This paper reviews the mainstream knowledge graph representation learning methods without auxiliary information, mainly, the distance-based and the semantic matching-based methods, and the knowledge graph representation learning methods containing textual auxiliary information and category auxiliary information, along with the advantages and the disadvantages of various representation learning methods. It is found that the introduction of auxiliary information can effectively represent new entities and relationships in the knowledge graph, but the time and space costs are significantly increased, and thus the methods without auxiliary information are more easily applied in practical scenarios at this stage. Finally, we show how the knowledge graph embedding can be applied to downstream tasks such as the triad classification, the link prediction and the recommender systems. A collection of datasets and open source libraries for different tasks is compiled and, and a comprehensive outlook on promising research directions such as large-scale, dynamic knowledge graphs is given.
knowledge graph
/
knowledge graph embedding
/
representation learning
/
deep learning
张翙, 杨伟杰, 刘文文, 张珣, 段大高, 韩忠明.
人工智能时代知识图谱表示学习方法体系.
科技导报,
2021
, 39
(22)
: 94
-110
.
DOI: 10.3981/j.issn.1000-7857.2021.22.011
ZHANG Hui, YANG Weijie, LIU Wenwen, ZHANG Xun, DUAN Dagao, HAN Zhongming.
Knowledge graph representation learning method system in the era of artificial intelligence[J].
Science & Technology Review ,
2021
, 39
(22)
: 94
-110
.
DOI: 10.3981/j.issn.1000-7857.2021.22.011
2021年第39卷第22期
PDF下载
1152
861
引用本文
BibTeX
文章信息
doi: 10.3981/j.issn.1000-7857.2021.22.011
接收时间：2021-03-13
首发时间：2021-12-21
出版时间：2021-11-28
收稿日期：2021-03-13
修回日期：2021-07-29
通讯作者:
杨伟杰(通信作者),讲师,研究方向为大数据分析与信息检索,电子信箱:yangwj@btbu.edu.cn
https://castjournals.cast.org.cn/joweb/kjdb/CN/10.3981/j.issn.1000-7857.2021.22.011
引用本文
BibTeX
2种不同金属材料的力学参数
科 属数 种数 占总种数比例 属 种数 占总种数比例 鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78 小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39 多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39 红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87 小菇属 Mycena 11 5.26 光柄菇属 Pluteus 5 2.39 红菇属 Russula 17 8.13 栓菌属 Trametes 5 2.39
关闭全屏
BibTeX
EndNote
RefWorks
TxT
PDF下载
全屏
1152
861
关闭全屏
北京市海淀区学院南路86号
010-62199257
qkjq@cast.org.cn
