GraRep: learning graph representations with global structural information

Shaosheng Cao, Wei Lu, Qiongkai Xu

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

1267 Citations (Scopus)

Abstract

In this paper, we present GraRep, a novel model for learning vertex representations of weighted graphs. This model learns low dimensional vectors to represent vertices appearing in a graph and, unlike existing work, integrates global structural information of the graph into the learning process. We also formally analyze the connections between our work and several previous research efforts, including the Deep-Walk model of Perozzi et al. [20] as well as the skip-gram model with negative sampling of Mikolov et al. [18] 

We conduct experiments on a language network, a social network as well as a citation network and show that our learned global representations can be effectively used as features in tasks such as clustering, classification and visualization. Empirical results demonstrate that our representation significantly outperforms other state-of-the-art methods in such tasks.

Original languageEnglish
Title of host publicationCIKM '15
Subtitle of host publicationproceedings of the 24th ACM International on Conference on Information and Knowledge Management
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages891-900
Number of pages10
ISBN (Electronic)9781450337946
DOIs
Publication statusPublished - 2015
Externally publishedYes
Event24th ACM International Conference on Information and Knowledge Management, CIKM 2015 - Melbourne, Australia
Duration: 19 Oct 201523 Oct 2015

Other

Other24th ACM International Conference on Information and Knowledge Management, CIKM 2015
Country/TerritoryAustralia
CityMelbourne
Period19/10/1523/10/15

Keywords

  • Graph Representation
  • Matrix Factorization
  • Feature Learning
  • Dimension Reduction

Fingerprint

Dive into the research topics of 'GraRep: learning graph representations with global structural information'. Together they form a unique fingerprint.

Cite this