Many heads are better than one

Local community detection by the multi-walker chain

Yuchen Bian, Jingchao Ni, Wei Cheng, Xiang Zhang

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

4 Citations (Scopus)

Abstract

Local community detection (or local clustering) is of fundamental importance in large network analysis. Random walk based methods have been routinely used in this task. Most existing random walk methods are based on the single-walker model. However, without any guidance, a single-walker may not be adequate to effectively capture the local cluster. In this paper, we study a multi-walker chain (MWC) model, which allows multiple walkers to explore the network. Each walker is influenced (or pulled back) by all other walkers when deciding the next steps. This helps the walkers to stay as a group and within the cluster. We introduce two measures based on the mean and standard deviation of the visiting probabilities of the walkers. These measures not only can accurately identify the local cluster, but also help detect the cluster center and boundary, which cannot be achieved by the existing single-walker methods. We provide rigorous theoretical foundation for MWC, and devise efficient algorithms to compute it. Extensive experimental results on a variety of real-world networks demonstrate that MWC outperforms the state-of-the-art local community detection methods by a large margin.

Original languageEnglish (US)
Title of host publicationProceedings - 17th IEEE International Conference on Data Mining, ICDM 2017
EditorsGeorge Karypis, Srinivas Alu, Vijay Raghavan, Xindong Wu, Lucio Miele
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages21-30
Number of pages10
ISBN (Electronic)9781538638347
DOIs
StatePublished - Dec 15 2017
Event17th IEEE International Conference on Data Mining, ICDM 2017 - New Orleans, United States
Duration: Nov 18 2017Nov 21 2017

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
Volume2017-November
ISSN (Print)1550-4786

Other

Other17th IEEE International Conference on Data Mining, ICDM 2017
CountryUnited States
CityNew Orleans
Period11/18/1711/21/17

Fingerprint

Electric network analysis

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Bian, Y., Ni, J., Cheng, W., & Zhang, X. (2017). Many heads are better than one: Local community detection by the multi-walker chain. In G. Karypis, S. Alu, V. Raghavan, X. Wu, & L. Miele (Eds.), Proceedings - 17th IEEE International Conference on Data Mining, ICDM 2017 (pp. 21-30). (Proceedings - IEEE International Conference on Data Mining, ICDM; Vol. 2017-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDM.2017.11
Bian, Yuchen ; Ni, Jingchao ; Cheng, Wei ; Zhang, Xiang. / Many heads are better than one : Local community detection by the multi-walker chain. Proceedings - 17th IEEE International Conference on Data Mining, ICDM 2017. editor / George Karypis ; Srinivas Alu ; Vijay Raghavan ; Xindong Wu ; Lucio Miele. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 21-30 (Proceedings - IEEE International Conference on Data Mining, ICDM).
@inproceedings{b1b561bba147481c8e03d3048ba8d72c,
title = "Many heads are better than one: Local community detection by the multi-walker chain",
abstract = "Local community detection (or local clustering) is of fundamental importance in large network analysis. Random walk based methods have been routinely used in this task. Most existing random walk methods are based on the single-walker model. However, without any guidance, a single-walker may not be adequate to effectively capture the local cluster. In this paper, we study a multi-walker chain (MWC) model, which allows multiple walkers to explore the network. Each walker is influenced (or pulled back) by all other walkers when deciding the next steps. This helps the walkers to stay as a group and within the cluster. We introduce two measures based on the mean and standard deviation of the visiting probabilities of the walkers. These measures not only can accurately identify the local cluster, but also help detect the cluster center and boundary, which cannot be achieved by the existing single-walker methods. We provide rigorous theoretical foundation for MWC, and devise efficient algorithms to compute it. Extensive experimental results on a variety of real-world networks demonstrate that MWC outperforms the state-of-the-art local community detection methods by a large margin.",
author = "Yuchen Bian and Jingchao Ni and Wei Cheng and Xiang Zhang",
year = "2017",
month = "12",
day = "15",
doi = "10.1109/ICDM.2017.11",
language = "English (US)",
series = "Proceedings - IEEE International Conference on Data Mining, ICDM",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "21--30",
editor = "George Karypis and Srinivas Alu and Vijay Raghavan and Xindong Wu and Lucio Miele",
booktitle = "Proceedings - 17th IEEE International Conference on Data Mining, ICDM 2017",
address = "United States",

}

Bian, Y, Ni, J, Cheng, W & Zhang, X 2017, Many heads are better than one: Local community detection by the multi-walker chain. in G Karypis, S Alu, V Raghavan, X Wu & L Miele (eds), Proceedings - 17th IEEE International Conference on Data Mining, ICDM 2017. Proceedings - IEEE International Conference on Data Mining, ICDM, vol. 2017-November, Institute of Electrical and Electronics Engineers Inc., pp. 21-30, 17th IEEE International Conference on Data Mining, ICDM 2017, New Orleans, United States, 11/18/17. https://doi.org/10.1109/ICDM.2017.11

Many heads are better than one : Local community detection by the multi-walker chain. / Bian, Yuchen; Ni, Jingchao; Cheng, Wei; Zhang, Xiang.

Proceedings - 17th IEEE International Conference on Data Mining, ICDM 2017. ed. / George Karypis; Srinivas Alu; Vijay Raghavan; Xindong Wu; Lucio Miele. Institute of Electrical and Electronics Engineers Inc., 2017. p. 21-30 (Proceedings - IEEE International Conference on Data Mining, ICDM; Vol. 2017-November).

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

TY - GEN

T1 - Many heads are better than one

T2 - Local community detection by the multi-walker chain

AU - Bian, Yuchen

AU - Ni, Jingchao

AU - Cheng, Wei

AU - Zhang, Xiang

PY - 2017/12/15

Y1 - 2017/12/15

N2 - Local community detection (or local clustering) is of fundamental importance in large network analysis. Random walk based methods have been routinely used in this task. Most existing random walk methods are based on the single-walker model. However, without any guidance, a single-walker may not be adequate to effectively capture the local cluster. In this paper, we study a multi-walker chain (MWC) model, which allows multiple walkers to explore the network. Each walker is influenced (or pulled back) by all other walkers when deciding the next steps. This helps the walkers to stay as a group and within the cluster. We introduce two measures based on the mean and standard deviation of the visiting probabilities of the walkers. These measures not only can accurately identify the local cluster, but also help detect the cluster center and boundary, which cannot be achieved by the existing single-walker methods. We provide rigorous theoretical foundation for MWC, and devise efficient algorithms to compute it. Extensive experimental results on a variety of real-world networks demonstrate that MWC outperforms the state-of-the-art local community detection methods by a large margin.

AB - Local community detection (or local clustering) is of fundamental importance in large network analysis. Random walk based methods have been routinely used in this task. Most existing random walk methods are based on the single-walker model. However, without any guidance, a single-walker may not be adequate to effectively capture the local cluster. In this paper, we study a multi-walker chain (MWC) model, which allows multiple walkers to explore the network. Each walker is influenced (or pulled back) by all other walkers when deciding the next steps. This helps the walkers to stay as a group and within the cluster. We introduce two measures based on the mean and standard deviation of the visiting probabilities of the walkers. These measures not only can accurately identify the local cluster, but also help detect the cluster center and boundary, which cannot be achieved by the existing single-walker methods. We provide rigorous theoretical foundation for MWC, and devise efficient algorithms to compute it. Extensive experimental results on a variety of real-world networks demonstrate that MWC outperforms the state-of-the-art local community detection methods by a large margin.

UR - http://www.scopus.com/inward/record.url?scp=85043993519&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043993519&partnerID=8YFLogxK

U2 - 10.1109/ICDM.2017.11

DO - 10.1109/ICDM.2017.11

M3 - Conference contribution

T3 - Proceedings - IEEE International Conference on Data Mining, ICDM

SP - 21

EP - 30

BT - Proceedings - 17th IEEE International Conference on Data Mining, ICDM 2017

A2 - Karypis, George

A2 - Alu, Srinivas

A2 - Raghavan, Vijay

A2 - Wu, Xindong

A2 - Miele, Lucio

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Bian Y, Ni J, Cheng W, Zhang X. Many heads are better than one: Local community detection by the multi-walker chain. In Karypis G, Alu S, Raghavan V, Wu X, Miele L, editors, Proceedings - 17th IEEE International Conference on Data Mining, ICDM 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 21-30. (Proceedings - IEEE International Conference on Data Mining, ICDM). https://doi.org/10.1109/ICDM.2017.11