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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Hierarchical graph attention network for temporal knowledge graph reasoning

文献类型：期刊论文

作者Shao, Pengpeng1; He, Jiayi1; Li, Guanjun1; Zhang, Dawei1; Tao, Jianhua2
刊名NEUROCOMPUTING
出版日期2023-09-14
卷号550页码:8
关键词Temporal knowledge graphs Graph attention network Reasoning
ISSN号0925-2312
DOI10.1016/j.neucom.2023.126390
通讯作者Tao, Jianhua(jhtao@tsinghua.edu.cn)
英文摘要Temporal knowledge graphs (TKGs) reasoning has attracted increasing research interest in recent years. However, most of the existing TKGs reasoning models aim to learn a dynamic entity representation by binding timestamps information with the entities, neglecting to learn adaptive entity representation that is valuable to the query from relevant historical facts. To this end, we propose a Hierarchical Graph Attention neTwork (HGAT) for the TKGs reasoning task. Specifically, we design a hierarchical neighbor encoder to model the time-oriented and task-oriented roles of the entities. The time-aware mechanism is developed in the first layer to differentiate the contributions of query-relevant historical facts at different timestamps to the query. The designed relation-aware attention is used in the second layer to discern the contributions of the structural neighbors of an entity. Through this hierarchical encoder, our model can absorb valuable knowledge effectively from the relevant historical facts, and thus learn more expressive adaptive entity representation for the query. Finally, we evaluate our model performance on four TKGs datasets and justify its superiority against vaerious state-of-the-art baselines. & COPY; 2023 Elsevier B.V. All rights reserved.
资助项目National Natural Science Foundation of China (NSFC)[61831022] ; National Natural Science Foundation of China (NSFC)[62276259] ; National Natural Science Foundation of China (NSFC)[62201572] ; National Natural Science Foundation of China (NSFC)[62206278] ; National Natural Science Foundation of China (NSFC)[U21B2010] ; Beijing Municipal Science amp; Technology Commission, Administrative Commission of Zhongguancun Science Park[Z211100004821013] ; CCF-Baidu Open Fund[OF2022025]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001038714700001
出版者ELSEVIER
资助机构National Natural Science Foundation of China (NSFC) ; Beijing Municipal Science amp; Technology Commission, Administrative Commission of Zhongguancun Science Park ; CCF-Baidu Open Fund
源URL[http://ir.ia.ac.cn/handle/173211/53843]  
专题多模态人工智能系统全国重点实验室
通讯作者Tao, Jianhua
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China
2.Tsinghua Univ, Dept Automat, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Shao, Pengpeng,He, Jiayi,Li, Guanjun,et al. Hierarchical graph attention network for temporal knowledge graph reasoning[J]. NEUROCOMPUTING,2023,550:8.
APA Shao, Pengpeng,He, Jiayi,Li, Guanjun,Zhang, Dawei,&Tao, Jianhua.(2023).Hierarchical graph attention network for temporal knowledge graph reasoning.NEUROCOMPUTING,550,8.
MLA Shao, Pengpeng,et al."Hierarchical graph attention network for temporal knowledge graph reasoning".NEUROCOMPUTING 550(2023):8.

入库方式： OAI收割

来源：自动化研究所

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。