DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jisung Yoon | - |
dc.contributor.author | JUNG, WOO SUNG | - |
dc.contributor.author | Kai-Cheng Yang | - |
dc.contributor.author | Yong-Yeol Ahn | - |
dc.date.accessioned | 2021-06-13T03:50:43Z | - |
dc.date.available | 2021-06-13T03:50:43Z | - |
dc.date.created | 2021-03-31 | - |
dc.date.issued | 2021-03 | - |
dc.identifier.issn | 2376-5992 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/106687 | - |
dc.description.abstract | Graph embedding techniques, which learn low-dimensional representations of a graph, are achieving state-of-the-art performance in many graph mining tasks. Most existing embedding algorithms assign a single vector to each node, implicitly assuming that a single representation is enough to capture all characteristics of the node. However, across many domains, it is common to observe pervasively overlapping community structure, where most nodes belong to multiple communities, playing different roles depending on the contexts. Here, we propose persona2vec, a graph embedding framework that efficiently learns multiple representations of nodes based on their structural contexts. Using link prediction-based evaluation, we show that our framework is significantly faster than the existing state-of-the-art model while achieving better performance. | - |
dc.language | English | - |
dc.publisher | PEERJ INC | - |
dc.relation.isPartOf | PEERJ COMPUTER SCIENCE | - |
dc.title | Persona2vec: a flexible multi-role representations learning framework for graphs | - |
dc.type | Article | - |
dc.identifier.doi | 10.7717/peerj-cs.439 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | PEERJ COMPUTER SCIENCE, v.7, pp.1 - 20 | - |
dc.identifier.wosid | 000636289800001 | - |
dc.citation.endPage | 20 | - |
dc.citation.startPage | 1 | - |
dc.citation.title | PEERJ COMPUTER SCIENCE | - |
dc.citation.volume | 7 | - |
dc.contributor.affiliatedAuthor | Jisung Yoon | - |
dc.contributor.affiliatedAuthor | JUNG, WOO SUNG | - |
dc.identifier.scopusid | 2-s2.0-85105697565 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | Graph embedding | - |
dc.subject.keywordAuthor | Overlapping community | - |
dc.subject.keywordAuthor | Social context | - |
dc.subject.keywordAuthor | Social network analysis | - |
dc.subject.keywordAuthor | Link prediction | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.