GraRep: learning graph representations with global structural information

Shaosheng Cao; Wei Lu; Qiongkai Xu

doi:10.1145/2806416.2806512

GraRep: learning graph representations with global structural information

Shaosheng Cao, Wei Lu, Qiongkai Xu

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

1598 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 language	English
Title of host publication	CIKM '15
Subtitle of host publication	proceedings of the 24th ACM International on Conference on Information and Knowledge Management
Place of Publication	New York
Publisher	Association for Computing Machinery, Inc
Pages	891-900
Number of pages	10
ISBN (Electronic)	9781450337946
DOIs	https://doi.org/10.1145/2806416.2806512
Publication status	Published - 2015
Externally published	Yes
Event	24th ACM International Conference on Information and Knowledge Management, CIKM 2015 - Melbourne, Australia Duration: 19 Oct 2015 → 23 Oct 2015

Other

Other	24th ACM International Conference on Information and Knowledge Management, CIKM 2015
Country/Territory	Australia
City	Melbourne
Period	19/10/15 → 23/10/15

Keywords

Graph Representation
Matrix Factorization
Feature Learning
Dimension Reduction

Access to Document

10.1145/2806416.2806512

Cite this

@inproceedings{ef9aa9f5e7d24a13ba122f07f80aff66,

title = "GraRep: learning graph representations with global structural information",

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.",

keywords = "Graph Representation, Matrix Factorization, Feature Learning, Dimension Reduction",

author = "Shaosheng Cao and Wei Lu and Qiongkai Xu",

year = "2015",

doi = "10.1145/2806416.2806512",

language = "English",

pages = "891--900",

booktitle = "CIKM '15",

publisher = "Association for Computing Machinery, Inc",

note = "24th ACM International Conference on Information and Knowledge Management, CIKM 2015 ; Conference date: 19-10-2015 Through 23-10-2015",

}

Cao, S, Lu, W & Xu, Q 2015, GraRep: learning graph representations with global structural information. in CIKM '15: proceedings of the 24th ACM International on Conference on Information and Knowledge Management. Association for Computing Machinery, Inc, New York, pp. 891-900, 24th ACM International Conference on Information and Knowledge Management, CIKM 2015, Melbourne, Australia, 19/10/15. https://doi.org/10.1145/2806416.2806512

GraRep: learning graph representations with global structural information. / Cao, Shaosheng; Lu, Wei; Xu, Qiongkai.
CIKM '15: proceedings of the 24th ACM International on Conference on Information and Knowledge Management. New York: Association for Computing Machinery, Inc, 2015. p. 891-900.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - GraRep

T2 - 24th ACM International Conference on Information and Knowledge Management, CIKM 2015

AU - Cao, Shaosheng

AU - Lu, Wei

AU - Xu, Qiongkai

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

KW - Graph Representation

KW - Matrix Factorization

KW - Feature Learning

KW - Dimension Reduction

UR - https://www.scopus.com/pages/publications/84958239002

U2 - 10.1145/2806416.2806512

DO - 10.1145/2806416.2806512

M3 - Conference proceeding contribution

SP - 891

EP - 900

BT - CIKM '15

PB - Association for Computing Machinery, Inc

CY - New York

Y2 - 19 October 2015 through 23 October 2015

ER -

GraRep: learning graph representations with global structural information

Abstract

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this