A link density clustering algorithm based on automatically selecting density peaks for overlapping community detection

Lan Huang, Guishen Wang, Yan Wang, Wei Pang, Qin Ma

Research output: Contribution to journalArticle

9 Citations (Scopus)
6 Downloads (Pure)

Abstract

In this paper, we proposed a link density clustering (LDC) method for overlapping community detection based on density peaks. We firstly use an extended cosine link distance metric to reflect the relationship of links. Then we introduce a clustering algorithm with fast search for solving the link clustering (LC) problem by density peaks with box plot strategy to determine the cluster centers automatically. Finally, we acquire both the link communities and the node communities. Our algorithm is compared with other representative algorithms through substantial experiments on real-world networks. The experimental results show that our algorithm consistently outperforms other algorithms in terms of modularity and coverage.


Original languageEnglish
Article number1650167
Number of pages15
JournalInternational Journal of Modern Physics B
Volume30
Issue number24
Early online date22 Jun 2016
DOIs
Publication statusPublished - 30 Sep 2016

Fingerprint

modularity
boxes
plots

Keywords

  • link community
  • overlapping community detection
  • link distance metric
  • box plot
  • complex network

Cite this

A link density clustering algorithm based on automatically selecting density peaks for overlapping community detection. / Huang, Lan; Wang, Guishen; Wang, Yan; Pang, Wei; Ma, Qin.

In: International Journal of Modern Physics B, Vol. 30, No. 24, 1650167, 30.09.2016.

Research output: Contribution to journalArticle

@article{528d044d31ab4b3fb03c18e731e530ba,
title = "A link density clustering algorithm based on automatically selecting density peaks for overlapping community detection",
abstract = "In this paper, we proposed a link density clustering (LDC) method for overlapping community detection based on density peaks. We firstly use an extended cosine link distance metric to reflect the relationship of links. Then we introduce a clustering algorithm with fast search for solving the link clustering (LC) problem by density peaks with box plot strategy to determine the cluster centers automatically. Finally, we acquire both the link communities and the node communities. Our algorithm is compared with other representative algorithms through substantial experiments on real-world networks. The experimental results show that our algorithm consistently outperforms other algorithms in terms of modularity and coverage.",
keywords = "link community, overlapping community detection, link distance metric, box plot, complex network",
author = "Lan Huang and Guishen Wang and Yan Wang and Wei Pang and Qin Ma",
year = "2016",
month = "9",
day = "30",
doi = "10.1142/S0217979216501678",
language = "English",
volume = "30",
journal = "International Journal of Modern Physics B",
issn = "0217-9792",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "24",

}

TY - JOUR

T1 - A link density clustering algorithm based on automatically selecting density peaks for overlapping community detection

AU - Huang, Lan

AU - Wang, Guishen

AU - Wang, Yan

AU - Pang, Wei

AU - Ma, Qin

PY - 2016/9/30

Y1 - 2016/9/30

N2 - In this paper, we proposed a link density clustering (LDC) method for overlapping community detection based on density peaks. We firstly use an extended cosine link distance metric to reflect the relationship of links. Then we introduce a clustering algorithm with fast search for solving the link clustering (LC) problem by density peaks with box plot strategy to determine the cluster centers automatically. Finally, we acquire both the link communities and the node communities. Our algorithm is compared with other representative algorithms through substantial experiments on real-world networks. The experimental results show that our algorithm consistently outperforms other algorithms in terms of modularity and coverage.

AB - In this paper, we proposed a link density clustering (LDC) method for overlapping community detection based on density peaks. We firstly use an extended cosine link distance metric to reflect the relationship of links. Then we introduce a clustering algorithm with fast search for solving the link clustering (LC) problem by density peaks with box plot strategy to determine the cluster centers automatically. Finally, we acquire both the link communities and the node communities. Our algorithm is compared with other representative algorithms through substantial experiments on real-world networks. The experimental results show that our algorithm consistently outperforms other algorithms in terms of modularity and coverage.

KW - link community

KW - overlapping community detection

KW - link distance metric

KW - box plot

KW - complex network

U2 - 10.1142/S0217979216501678

DO - 10.1142/S0217979216501678

M3 - Article

VL - 30

JO - International Journal of Modern Physics B

JF - International Journal of Modern Physics B

SN - 0217-9792

IS - 24

M1 - 1650167

ER -