Statistical inference for community detection in signed networks

Xuehua Zhao, Bo Yang, Xueyan Liu, and Huiling Chen
Phys. Rev. E 95, 042313 – Published 17 April 2017

Abstract

The problem of community detection in networks has received wide attention and proves to be computationally challenging. In recent years, with the surge of signed networks with positive links and negative links, to find community structure in such signed networks has become a research focus in the area of network science. Although many methods have been proposed to address the problem, their performance seriously depends on the predefined optimization objectives or heuristics which are usually difficult to accurately describe the intrinsic structure of community. In this study, we present a statistical inference method for community detection in signed networks, in which a probabilistic model is proposed to model signed networks and the expectation-maximization–based parameter estimation method is deduced to find communities in signed networks. In addition, to efficiently analyze signed networks without any a priori information, a model selection criterion is also proposed to automatically determine the number of communities. In our experiments, the proposed method is tested in the synthetic and real-word signed networks and compared with current methods. The experimental results show the proposed method can more efficiently and accurately find the communities in signed networks than current methods. Notably, the proposed method is a mathematically principled method.

  • Figure
  • Figure
  • Figure
  • Figure
  • Figure
  • Figure
  • Figure
  • Received 27 November 2016
  • Revised 11 February 2017

DOI:https://doi.org/10.1103/PhysRevE.95.042313

©2017 American Physical Society

Physics Subject Headings (PhySH)

NetworksStatistical Physics & Thermodynamics

Authors & Affiliations

Xuehua Zhao1,2,*, Bo Yang2,3,†, Xueyan Liu1,2,3, and Huiling Chen4

  • 1School of Digital Media, Shenzhen Institute of Information Technology, Shenzhen 518172, China
  • 2Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
  • 3College of Computer Science and Technology, Jilin University, Changchun 130012, China
  • 4College of Physics and Electronic Information, Wenzhou University, Wenzhou 325035, China

  • *lcrlc@sina.com
  • ybo@jlu.edu.cn

Article Text (Subscription Required)

Click to Expand

References (Subscription Required)

Click to Expand
Issue

Vol. 95, Iss. 4 — April 2017

Reuse & Permissions
Access Options
Author publication services for translation and copyediting assistance advertisement

Authorization Required


×
×

Images

×

Sign up to receive regular email alerts from Physical Review E

Log In

Cancel
×

Search


Article Lookup

Paste a citation or DOI

Enter a citation
×