Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization

Xiaohua Shi; Hongtao Lu; Yangchen He; Shan He

doi:10.1145/2808797.2809383

Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization

Xiaohua Shi, Hongtao Lu, Yangchen He, Shan He

Computer Science

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

29 Citations (Scopus)

Abstract

Non-negative Matrix Factorization (NMF) aims to find two non-negative matrices whose product approximates the original matrix well, and is widely used in clustering condition with good physical interpretability and universal applicability. Detecting communities with NMF can keep non-negative network physical definition and effectively capture communities-based structure in the low dimensional data space. However some NMF methods in community detection did not concern with more network inner structures or existing ground-truth community information. In this paper, we propose a novel pairwisely constrained nonnegative symmetric matrix factorization (PCSNMF) method, which not only consider symmetric community structures of undirected network, but also takes into consideration the pairwise constraints generated from some ground-truth group information to enhance the community detection. We compare our approaches with other NMF-based methods in three social networks, and experimental results for community detection show that our approaches are all feasible and achieve better community detection results.

Original language	English
Title of host publication	Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015
Editors	Jian Pei, Jie Tang, Fabrizio Silvestri
Publisher	Association for Computing Machinery
Pages	541-546
Number of pages	6
ISBN (Electronic)	9781450338547
DOIs	https://doi.org/10.1145/2808797.2809383
Publication status	Published - 25 Aug 2015
Event	IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015 - Paris, France Duration: 25 Aug 2015 → 28 Aug 2015

Publication series

Name	Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015

Conference

Conference	IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015
Country/Territory	France
City	Paris
Period	25/08/15 → 28/08/15

Bibliographical note

Funding Information:
A. Acknowledgments This work was supported by NSFC (no. 61272247 and 60873133), the Science and Technology Commission of Shanghai Municipality (Grant No. 13511500200), 863(No.2008AA02Z310) in China, the Arts and Science Cross Special Fund of Shanghai Jiao Tong University under Grant 13JCY14.

Publisher Copyright:
© 2015 ACM.

Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.

Keywords

Community detection
Non-negative Matrix Factorization
Pairwise constraints
Semi-supervised learning
Symmetric matrix

ASJC Scopus subject areas

Computer Science Applications
Computer Networks and Communications

Access to Document

10.1145/2808797.2809383

Cite this

Shi, X., Lu, H., He, Y., & He, S. (2015). Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization. In J. Pei, J. Tang, & F. Silvestri (Eds.), Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015 (pp. 541-546). (Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015). Association for Computing Machinery . https://doi.org/10.1145/2808797.2809383

Shi, Xiaohua ; Lu, Hongtao ; He, Yangchen et al. / Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization. Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015. editor / Jian Pei ; Jie Tang ; Fabrizio Silvestri. Association for Computing Machinery , 2015. pp. 541-546 (Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015).

@inproceedings{72174bb3ce2f485bb376989531d0bf07,

title = "Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization",

abstract = "Non-negative Matrix Factorization (NMF) aims to find two non-negative matrices whose product approximates the original matrix well, and is widely used in clustering condition with good physical interpretability and universal applicability. Detecting communities with NMF can keep non-negative network physical definition and effectively capture communities-based structure in the low dimensional data space. However some NMF methods in community detection did not concern with more network inner structures or existing ground-truth community information. In this paper, we propose a novel pairwisely constrained nonnegative symmetric matrix factorization (PCSNMF) method, which not only consider symmetric community structures of undirected network, but also takes into consideration the pairwise constraints generated from some ground-truth group information to enhance the community detection. We compare our approaches with other NMF-based methods in three social networks, and experimental results for community detection show that our approaches are all feasible and achieve better community detection results.",

keywords = "Community detection, Non-negative Matrix Factorization, Pairwise constraints, Semi-supervised learning, Symmetric matrix",

author = "Xiaohua Shi and Hongtao Lu and Yangchen He and Shan He",

note = "Funding Information: A. Acknowledgments This work was supported by NSFC (no. 61272247 and 60873133), the Science and Technology Commission of Shanghai Municipality (Grant No. 13511500200), 863(No.2008AA02Z310) in China, the Arts and Science Cross Special Fund of Shanghai Jiao Tong University under Grant 13JCY14. Publisher Copyright: {\textcopyright} 2015 ACM. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.; IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015 ; Conference date: 25-08-2015 Through 28-08-2015",

year = "2015",

month = aug,

day = "25",

doi = "10.1145/2808797.2809383",

language = "English",

series = "Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015",

publisher = "Association for Computing Machinery ",

pages = "541--546",

editor = "Jian Pei and Jie Tang and Fabrizio Silvestri",

booktitle = "Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015",

}

Shi, X, Lu, H, He, Y & He, S 2015, Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization. in J Pei, J Tang & F Silvestri (eds), Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015. Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015, Association for Computing Machinery , pp. 541-546, IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015, Paris, France, 25/08/15. https://doi.org/10.1145/2808797.2809383

Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization. / Shi, Xiaohua; Lu, Hongtao; He, Yangchen et al.
Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015. ed. / Jian Pei; Jie Tang; Fabrizio Silvestri. Association for Computing Machinery , 2015. p. 541-546 (Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015).

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

TY - GEN

T1 - Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization

AU - Shi, Xiaohua

AU - Lu, Hongtao

AU - He, Yangchen

AU - He, Shan

N1 - Funding Information: A. Acknowledgments This work was supported by NSFC (no. 61272247 and 60873133), the Science and Technology Commission of Shanghai Municipality (Grant No. 13511500200), 863(No.2008AA02Z310) in China, the Arts and Science Cross Special Fund of Shanghai Jiao Tong University under Grant 13JCY14. Publisher Copyright: © 2015 ACM. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2015/8/25

Y1 - 2015/8/25

N2 - Non-negative Matrix Factorization (NMF) aims to find two non-negative matrices whose product approximates the original matrix well, and is widely used in clustering condition with good physical interpretability and universal applicability. Detecting communities with NMF can keep non-negative network physical definition and effectively capture communities-based structure in the low dimensional data space. However some NMF methods in community detection did not concern with more network inner structures or existing ground-truth community information. In this paper, we propose a novel pairwisely constrained nonnegative symmetric matrix factorization (PCSNMF) method, which not only consider symmetric community structures of undirected network, but also takes into consideration the pairwise constraints generated from some ground-truth group information to enhance the community detection. We compare our approaches with other NMF-based methods in three social networks, and experimental results for community detection show that our approaches are all feasible and achieve better community detection results.

AB - Non-negative Matrix Factorization (NMF) aims to find two non-negative matrices whose product approximates the original matrix well, and is widely used in clustering condition with good physical interpretability and universal applicability. Detecting communities with NMF can keep non-negative network physical definition and effectively capture communities-based structure in the low dimensional data space. However some NMF methods in community detection did not concern with more network inner structures or existing ground-truth community information. In this paper, we propose a novel pairwisely constrained nonnegative symmetric matrix factorization (PCSNMF) method, which not only consider symmetric community structures of undirected network, but also takes into consideration the pairwise constraints generated from some ground-truth group information to enhance the community detection. We compare our approaches with other NMF-based methods in three social networks, and experimental results for community detection show that our approaches are all feasible and achieve better community detection results.

KW - Community detection

KW - Non-negative Matrix Factorization

KW - Pairwise constraints

KW - Semi-supervised learning

KW - Symmetric matrix

UR - http://www.scopus.com/inward/record.url?scp=84962534288&partnerID=8YFLogxK

U2 - 10.1145/2808797.2809383

DO - 10.1145/2808797.2809383

M3 - Conference contribution

AN - SCOPUS:84962534288

T3 - Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015

SP - 541

EP - 546

BT - Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015

A2 - Pei, Jian

A2 - Tang, Jie

A2 - Silvestri, Fabrizio

PB - Association for Computing Machinery

T2 - IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015

Y2 - 25 August 2015 through 28 August 2015

ER -

Shi X, Lu H, He Y, He S. Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization. In Pei J, Tang J, Silvestri F, editors, Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015. Association for Computing Machinery . 2015. p. 541-546. (Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2015). doi: 10.1145/2808797.2809383

Community detection in social network with pairwisely constrained symmetric non-negative Matrix Factorization

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this