Probabilistic community discovery using hierarchical latent gaussian mixture model

Haizheng Zhang, C. Lee Giles, Henry C. Foley, John Yen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

48 Citations (Scopus)

Abstract

Complex networks exist in a wide array of diverse domains, ranging from biology, sociology, and computer science. These real-world networks, while disparate in nature, often comprise of a set of loose clusters(a.k.a communities), whose members are better connected to each other than to the rest of the network. Discovering such inherent community structures can lead to deeper understanding about the networks and therefore has raised increasing interests among researchers from various disciplines. This paper describes GWNLDA(Generic weighted network-Latent Dirichlet Allocation) model, a hierarchical Bayesian model derived from the widely-received LDA model, for discovering probabilistic community profiles in social networks. In this model, communities are modeled as latent variables and defined as distributions over the social actor space. In addition, each social actor belongs to every community with different probability. This paper also proposes two different network encoding approaches and explores the impact of these two approaches to the community discovery performance. This model is evaluated on two research collaborative networks:CiteSeer and NanoSCI. The experimental results demonstrate that this approach is promising for discovering community structures in large-scale networks.

Original languageEnglish (US)
Title of host publicationAAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference
Pages663-668
Number of pages6
Volume1
StatePublished - 2007
EventAAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference - Vancouver, BC, Canada
Duration: Jul 22 2007Jul 26 2007

Other

OtherAAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference
CountryCanada
CityVancouver, BC
Period7/22/077/26/07

Fingerprint

Complex networks
Computer science

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Zhang, H., Lee Giles, C., Foley, H. C., & Yen, J. (2007). Probabilistic community discovery using hierarchical latent gaussian mixture model. In AAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference (Vol. 1, pp. 663-668)
Zhang, Haizheng ; Lee Giles, C. ; Foley, Henry C. ; Yen, John. / Probabilistic community discovery using hierarchical latent gaussian mixture model. AAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference. Vol. 1 2007. pp. 663-668
@inproceedings{73bf08578c954c95b02ea7a04e153328,
title = "Probabilistic community discovery using hierarchical latent gaussian mixture model",
abstract = "Complex networks exist in a wide array of diverse domains, ranging from biology, sociology, and computer science. These real-world networks, while disparate in nature, often comprise of a set of loose clusters(a.k.a communities), whose members are better connected to each other than to the rest of the network. Discovering such inherent community structures can lead to deeper understanding about the networks and therefore has raised increasing interests among researchers from various disciplines. This paper describes GWNLDA(Generic weighted network-Latent Dirichlet Allocation) model, a hierarchical Bayesian model derived from the widely-received LDA model, for discovering probabilistic community profiles in social networks. In this model, communities are modeled as latent variables and defined as distributions over the social actor space. In addition, each social actor belongs to every community with different probability. This paper also proposes two different network encoding approaches and explores the impact of these two approaches to the community discovery performance. This model is evaluated on two research collaborative networks:CiteSeer and NanoSCI. The experimental results demonstrate that this approach is promising for discovering community structures in large-scale networks.",
author = "Haizheng Zhang and {Lee Giles}, C. and Foley, {Henry C.} and John Yen",
year = "2007",
language = "English (US)",
isbn = "1577353234",
volume = "1",
pages = "663--668",
booktitle = "AAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference",

}

Zhang, H, Lee Giles, C, Foley, HC & Yen, J 2007, Probabilistic community discovery using hierarchical latent gaussian mixture model. in AAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference. vol. 1, pp. 663-668, AAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference, Vancouver, BC, Canada, 7/22/07.

Probabilistic community discovery using hierarchical latent gaussian mixture model. / Zhang, Haizheng; Lee Giles, C.; Foley, Henry C.; Yen, John.

AAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference. Vol. 1 2007. p. 663-668.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Probabilistic community discovery using hierarchical latent gaussian mixture model

AU - Zhang, Haizheng

AU - Lee Giles, C.

AU - Foley, Henry C.

AU - Yen, John

PY - 2007

Y1 - 2007

N2 - Complex networks exist in a wide array of diverse domains, ranging from biology, sociology, and computer science. These real-world networks, while disparate in nature, often comprise of a set of loose clusters(a.k.a communities), whose members are better connected to each other than to the rest of the network. Discovering such inherent community structures can lead to deeper understanding about the networks and therefore has raised increasing interests among researchers from various disciplines. This paper describes GWNLDA(Generic weighted network-Latent Dirichlet Allocation) model, a hierarchical Bayesian model derived from the widely-received LDA model, for discovering probabilistic community profiles in social networks. In this model, communities are modeled as latent variables and defined as distributions over the social actor space. In addition, each social actor belongs to every community with different probability. This paper also proposes two different network encoding approaches and explores the impact of these two approaches to the community discovery performance. This model is evaluated on two research collaborative networks:CiteSeer and NanoSCI. The experimental results demonstrate that this approach is promising for discovering community structures in large-scale networks.

AB - Complex networks exist in a wide array of diverse domains, ranging from biology, sociology, and computer science. These real-world networks, while disparate in nature, often comprise of a set of loose clusters(a.k.a communities), whose members are better connected to each other than to the rest of the network. Discovering such inherent community structures can lead to deeper understanding about the networks and therefore has raised increasing interests among researchers from various disciplines. This paper describes GWNLDA(Generic weighted network-Latent Dirichlet Allocation) model, a hierarchical Bayesian model derived from the widely-received LDA model, for discovering probabilistic community profiles in social networks. In this model, communities are modeled as latent variables and defined as distributions over the social actor space. In addition, each social actor belongs to every community with different probability. This paper also proposes two different network encoding approaches and explores the impact of these two approaches to the community discovery performance. This model is evaluated on two research collaborative networks:CiteSeer and NanoSCI. The experimental results demonstrate that this approach is promising for discovering community structures in large-scale networks.

UR - http://www.scopus.com/inward/record.url?scp=36349023766&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36349023766&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:36349023766

SN - 1577353234

SN - 9781577353232

VL - 1

SP - 663

EP - 668

BT - AAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference

ER -

Zhang H, Lee Giles C, Foley HC, Yen J. Probabilistic community discovery using hierarchical latent gaussian mixture model. In AAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference. Vol. 1. 2007. p. 663-668