Institute of Computing Technology, Chinese Academy IR
Path-specific knowledge graph embedding | |
Jia, Yantao; Wang, Yuanzhuo; Jin, Xiaolong; Cheng, Xueqi | |
2018-07-01 | |
发表期刊 | KNOWLEDGE-BASED SYSTEMS |
ISSN | 0950-7051 |
卷号 | 151页码:37-44 |
摘要 | Knowledge graph embedding aims to represent entities, relations and multi-step relation paths of a knowledge graph as vectors in low-dimensional vector spaces, and supports many applications, such as entity prediction, relation prediction, etc. Existing embedding methods learn the representations of entities, relations, and multi-step relation paths by minimizing a general margin-based loss function shared by all relation paths. This setting fails to consider the differences among different relation paths. In this paper, we propose an embedding method by minimizing a path-specific margin-based loss function for knowledge graph embedding, called PaSKoGE. For each path, it adaptively determines its margin-based loss function by encoding the correlation between relations and multi-step relation paths for any given pair of entities. PaSKoGE outperforms the-state-of-the-art methods. (C) 2018 Elsevier B.V. All rights reserved. |
关键词 | Path-specific Knowledge graph embedding Relation path |
DOI | 10.1016/j.knosys.2018.03.020 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China[2016YFB1000902] ; National Grand Fundamental Research 973 Program of China[2012CB316303] ; National Grand Fundamental Research 973 Program of China[2014CB340401] ; National Natural Science Foundation of China[61402442] ; National Natural Science Foundation of China[61572469] ; National Natural Science Foundation of China[91646120] ; National Natural Science Foundation of China[61572473] ; National Natural Science Foundation of China[61303244] ; National Natural Science Foundation of China[61402124] |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000433655600004 |
出版者 | ELSEVIER SCIENCE BV |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://119.78.100.204/handle/2XEOYT63/5180 |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Jia, Yantao |
作者单位 | Chinese Acad Sci, Key Lab Network Data Sci & Technol, Inst Comp Technol, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Jia, Yantao,Wang, Yuanzhuo,Jin, Xiaolong,et al. Path-specific knowledge graph embedding[J]. KNOWLEDGE-BASED SYSTEMS,2018,151:37-44. |
APA | Jia, Yantao,Wang, Yuanzhuo,Jin, Xiaolong,&Cheng, Xueqi.(2018).Path-specific knowledge graph embedding.KNOWLEDGE-BASED SYSTEMS,151,37-44. |
MLA | Jia, Yantao,et al."Path-specific knowledge graph embedding".KNOWLEDGE-BASED SYSTEMS 151(2018):37-44. |
条目包含的文件 | 条目无相关文件。 |
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。
修改评论