CASIA OpenIR
HiWalk: Learning node embeddings from heterogeneous networks
Bai, Jie1,2; Li, Linjing1; Zeng, Daniel1,3
Source PublicationINFORMATION SYSTEMS
ISSN0306-4379
2019-03-01
Volume81Pages:82-91
Corresponding AuthorBai, Jie(baijie2013@ia.ac.cn) ; Li, Linjing(linjing.li@ia.ac.cn)
AbstractHeterogeneous networks, such as bibliographical networks and online business networks, are ubiquitous in everyday life. Nevertheless, analyzing them for high-level semantic understanding still poses a great challenge for modern information systems. In this paper, we propose HiWalk to learn distributed vector representations of the nodes in heterogeneous networks. HiWalk is inspired by the state-of-the-art representation learning algorithms employed in the context of both homogeneous networks and heterogeneous networks, based on word embedding learning models. Different from existing methods in the literature, the purpose of HiWalk is to learn vector representations of the targeted set of nodes by leveraging the other nodes as "background knowledge", which maximizes the structural correlations of contiguous nodes. HiWalk decomposes the adjacent probabilities of the nodes and adopts a hierarchical random walk strategy, which makes it more effective, efficient and concentrated when applied to practical large-scale heterogeneous networks. HiWalk can be widely applied in heterogeneous networks environments to analyze targeted types of nodes. We further validate the effectiveness of the proposed HiWalk through multiple tasks conducted on two real-world datasets. (C) 2018 Elsevier Ltd. All rights reserved.
KeywordNetwork analysis Representation learning Behavioral analysis Random walk Heterogeneous network
DOI10.1016/j.is.2018.11.008
WOS KeywordFRAMEWORK
Indexed BySCI
Language英语
Funding ProjectNational Key R&D Program of China[2016QY02D0305] ; National Natural Science Foundation of China[71621002] ; National Natural Science Foundation of China[71602184] ; National Natural Science Foundation of China[71202169] ; National Natural Science Foundation of China[61671450] ; National Natural Science Foundation of China[U1435221] ; Key Research Program of the Chinese Academy of Sciences[ZDRW-XH-2017-3]
Funding OrganizationNational Key R&D Program of China ; National Natural Science Foundation of China ; Key Research Program of the Chinese Academy of Sciences
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems
WOS IDWOS:000459839400005
PublisherPERGAMON-ELSEVIER SCIENCE LTD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/25001
Collection中国科学院自动化研究所
Corresponding AuthorBai, Jie; Li, Linjing
Affiliation1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China
3.Univ Arizona, Dept Management Informat Syst, Tucson, AZ 85721 USA
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Bai, Jie,Li, Linjing,Zeng, Daniel. HiWalk: Learning node embeddings from heterogeneous networks[J]. INFORMATION SYSTEMS,2019,81:82-91.
APA Bai, Jie,Li, Linjing,&Zeng, Daniel.(2019).HiWalk: Learning node embeddings from heterogeneous networks.INFORMATION SYSTEMS,81,82-91.
MLA Bai, Jie,et al."HiWalk: Learning node embeddings from heterogeneous networks".INFORMATION SYSTEMS 81(2019):82-91.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Bai, Jie]'s Articles
[Li, Linjing]'s Articles
[Zeng, Daniel]'s Articles
Baidu academic
Similar articles in Baidu academic
[Bai, Jie]'s Articles
[Li, Linjing]'s Articles
[Zeng, Daniel]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Bai, Jie]'s Articles
[Li, Linjing]'s Articles
[Zeng, Daniel]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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