Length of clustering algorithms based on random walks with an application to neuroscience

Michèle Thieullen and Alexis Vigot

Chaos, Solitons & Fractals, 2012, vol. 45, issue 5, 629-639

Abstract: In this paper we show how the notions of conductance and cutoff can be used to determine the length of the random walks in some clustering algorithms. We consider graphs which are globally sparse but locally dense. They present a community structure: there exists a partition of the set of vertices into subsets which display strong internal connections but few links between each other. Using a distance between nodes built on random walks we consider a hierarchical clustering algorithm which provides a most appropriate partition. The length of these random walks has to be chosen in advance and has to be appropriate. Finally, we introduce an extension of this clustering algorithm to dynamical sequences of graphs on the same set of vertices.

Date: 2012
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960077912000720
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:chsofr:v:45:y:2012:i:5:p:629-639

DOI: 10.1016/j.chaos.2012.02.021

Access Statistics for this article

Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros

More articles in Chaos, Solitons & Fractals from Elsevier
Bibliographic data for series maintained by Thayer, Thomas R. ().