Title: Multi-scale community detection using stability optimisation

Authors: Erwan Le Martelot; Chris Hankin

Addresses: Department of Computing Imperial College London, London SW7 2AZ, UK ' Department of Computing Imperial College London, London SW7 2AZ, UK

Abstract: Many real systems can be represented as networks whose analysis can be very informative regarding the original system's organisation. In the past decade, community detection received a lot of attention and is now a very active field of research. Recently, stability was introduced as a new measure for partition quality. This work investigates stability as an optimisation criterion that exploits a Markov process view of networks to enable multi-scale community detection. Several heuristics and variations of an algorithm optimising stability are presented as well as an application to overlapping communities. Experiments show that the method enables accurate multi-scale network analysis.

Keywords: multi-scale community detection; stability; Markov process; random walks; overlapping communities; partition quality; optimisation criterion; online communities; virtual communities; web based communities; multi-scale network analysis.

DOI: 10.1504/IJWBC.2013.054907

International Journal of Web Based Communities, 2013 Vol.9 No.3, pp.323 - 348

Published online: 27 May 2013 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article