HackRL: Reinforcement learning with hierarchical attention for cross-graph knowledge fusion and collaborative reasoning
Yang, Linyao1,2; Wang, Xiao1,3; Dai, Yuxin4; Xin, Kejun3,5; Zheng, Xiaolong1; Ding, Weiping6; Zhang, Jun1,3,4; Wang, Fei-Yue1,3
Source PublicationKNOWLEDGE-BASED SYSTEMS
ISSN0950-7051
2021-12-05
Volume233Pages:14
Abstract

Reasoning aiming at inferring implicit facts over knowledge graphs (KGs) is a critical and fundamental task for various intelligent knowledge-based services. With multiple distributed and complementary KGs, the effective and efficient capture and fusion of knowledge from different KGs is becoming an increasingly important topic, which has not been well studied. To fill this gap, we propose to explore cross-KG relation paths with the anchor links identified by entity alignment for the knowledge fusion and collaborative reasoning of multiple KGs. To address the heterogeneity of different KGs, this paper proposes a novel reasoning model named HackRL based on the reinforcement learning framework, which incorporates the long short-term memory and hierarchical graph attention in the policy network to infer indicative cross-KG relation paths from the history trajectory and the heterogeneous environment for predicting corresponding relations. Meanwhile, an entity alignment oriented representation learning method is utilized to embed different KGs into a unified vector space based on the anchor links to reduce the impact of distinct vector spaces, and two training mechanisms, action mask and retrain with sampled paths, are proposed to optimize the training process to learn more successful indicative paths. The proposed HackRL is validated on three cross-lingual datasets built from DBpedia on the link prediction and fact prediction tasks. Experimental results demonstrate that HackRL achieves better performance on most tasks than existing methods. This work provides an industrially-applicable framework for fusing distributed KGs to make better decisions. (c) 2021 Elsevier B.V. All rights reserved.

KeywordKnowledge fusion Knowledge reasoning Decision-making Hierarchical graph attention Reinforcement learning
DOI10.1016/j.knosys.2021.107498
WOS KeywordFRAMEWORK
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000709919000011
PublisherELSEVIER
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/46265
Collection复杂系统管理与控制国家重点实验室_平行智能技术与系统团队
复杂系统管理与控制国家重点实验室_互联网大数据与信息安全
Corresponding AuthorWang, Xiao
Affiliation1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Qingdao Acad Intelligent Ind, Qingdao 266000, Peoples R China
4.Wuhan Univ, Sch Elect Engn & Automat, Wuhan 430072, Peoples R China
5.Nanjing Joinmap Data Res Inst, Nanjing 211100, Peoples R China
6.Nantong Univ, Sch Informat Sci & Technol, Nantong 226019, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Yang, Linyao,Wang, Xiao,Dai, Yuxin,et al. HackRL: Reinforcement learning with hierarchical attention for cross-graph knowledge fusion and collaborative reasoning[J]. KNOWLEDGE-BASED SYSTEMS,2021,233:14.
APA Yang, Linyao.,Wang, Xiao.,Dai, Yuxin.,Xin, Kejun.,Zheng, Xiaolong.,...&Wang, Fei-Yue.(2021).HackRL: Reinforcement learning with hierarchical attention for cross-graph knowledge fusion and collaborative reasoning.KNOWLEDGE-BASED SYSTEMS,233,14.
MLA Yang, Linyao,et al."HackRL: Reinforcement learning with hierarchical attention for cross-graph knowledge fusion and collaborative reasoning".KNOWLEDGE-BASED SYSTEMS 233(2021):14.
Files in This Item: Download All
File Name/Size DocType Version Access License
1-s2.0-S095070512100(1159KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang, Linyao]'s Articles
[Wang, Xiao]'s Articles
[Dai, Yuxin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang, Linyao]'s Articles
[Wang, Xiao]'s Articles
[Dai, Yuxin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang, Linyao]'s Articles
[Wang, Xiao]'s Articles
[Dai, Yuxin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 1-s2.0-S0950705121007607-main.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.