Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/80424
PIRA download icon_1.1View/Download Full Text
DC FieldValueLanguage
dc.contributorDepartment of Chinese and Bilingual Studies-
dc.contributorDepartment of Computing-
dc.creatorLong, YF-
dc.creatorXiang, R-
dc.creatorLu, Q-
dc.creatorXiong, D-
dc.creatorHuang, CR-
dc.creatorBi, CL-
dc.creatorLi, ML-
dc.date.accessioned2019-03-26T09:17:05Z-
dc.date.available2019-03-26T09:17:05Z-
dc.identifier.issn2169-3536-
dc.identifier.urihttp://hdl.handle.net/10397/80424-
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.rights© 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.en_US
dc.rightsPost with permission of the publisher.en_US
dc.rightsThe following publication Long, Y.F., Xiang, R., Lu, Q., Xiong, D., Huang, C.R., Bi, C.L., & Li, M.L. (2018). Learning heterogeneous network embedding from text and links. IEEE Access, 6, 55850-55860 is available at https://dx.doi.org/10.1109/ACCESS.2018.2873044en_US
dc.subjectNetwork embeddingen_US
dc.subjectHeterogeneous networken_US
dc.subjectAttention mechanismen_US
dc.subjectText processingen_US
dc.titleLearning heterogeneous network embedding from text and linksen_US
dc.typeJournal/Magazine Articleen_US
dc.identifier.spage55850-
dc.identifier.epage55860-
dc.identifier.volume6-
dc.identifier.doi10.1109/ACCESS.2018.2873044-
dcterms.abstractFinding methods to represent multiple types of nodes in heterogeneous networks is both challenging and rewarding, as there is much less work in this area compared with that of homogeneous networks. In this paper, we propose a novel approach to learn node embedding for heterogeneous networks through a joint learning framework of both network links and text associated with nodes. A novel attention mechanism is also used to make good use of text extended through links to obtain much larger network context. Link embedding is first learned through a random-walk-based method to process multiple types of links. Text embedding is separately learned at both sentence level and document level to capture salient semantic information more comprehensively. Then, both types of embeddings are jointly fed into a hierarchical neural network model to learn node representation through mutual enhancement. The attention mechanism follows linked edges to obtain context of adjacent nodes to extend context for node representation. The evaluation on a link prediction task in a heterogeneous network data set shows that our method outperforms the current state-of-the-art method by 2.5%-5.0% in AUC values with p-value less than 10(-9), indicating very significant improvement.-
dcterms.accessRightsopen accessen_US
dcterms.bibliographicCitationIEEE access, 2018, v. 6, p. 55850-55860-
dcterms.isPartOfIEEE access-
dcterms.issued2018-
dc.identifier.isiWOS:000448288800001-
dc.description.validate201903 bcrc-
dc.description.oaVersion of Recorden_US
dc.identifier.FolderNumberOA_IR/PIRAen_US
dc.description.pubStatusPublisheden_US
Appears in Collections:Journal/Magazine Article
Files in This Item:
File Description SizeFormat 
Long_Learning_Heterogeneous_Network.pdf7.59 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

Page views

114
Last Week
1
Last month
Citations as of Mar 24, 2024

Downloads

145
Citations as of Mar 24, 2024

SCOPUSTM   
Citations

2
Citations as of Mar 29, 2024

WEB OF SCIENCETM
Citations

2
Citations as of Mar 28, 2024

Google ScholarTM

Check

Altmetric


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