Community Detection Modularity Suite Icon

Community Detection Modularity Suite

Suite of community detection algorithms based on Modularity

Add a Review
1 Download (This Week)
Last Update:
Download CDMSuite_cpp.tar.gz
Browse All Files
Linux

Screenshots

Description

- MixtureModel_v1r1: overlapping community algorithm [3], which includes novel partition density and fuzzy modularity metrics.

- OpenMP versions of algorithms in [1] are available to download.

- Main suite containing three community detection algorithms based on the Modularity measure containing: Geodesic and Random Walk edge Betweenness [1] and Spectral Modularity [2].


Collaborator: Theologos Kotsos.

[1] M. Newman & M. Girvan, Physical Review, E 69 (026113), 2004.
[2] M. Newman, Physical Review E, 74(3):036104, 2006.
[3] B. Ball et al, An efficient and principled method for detecting communities in networks, 2011.
The suite is based upon the fast community algorithm implemented by Aaron Clauset <aaron@cs.unm.edu>, Chris Moore, Mark Newman, and the R IGraph library Copyright (C) 2007 Gabor Csardi <csardi@rmki.kfki.hu>. It also makes of the classes available from Numerical Recipies 3rd Edition W. Press, S. Teukolsky, W. Vetterling, B. Flanne

Community Detection Modularity Suite Web Site

Features

  • C++ and R implementations of Newman & Girvan Modularity based community detection algorithms
  • R implementations of the edge Betweenness Random Walk algorithm
  • Boot-strapping factilities to test cluster robustness
  • Version 2 (v2r1) contains OpenMP implementation of Newman & Girvan Geodesic and Random Walk edge Betweenness algorithms
  • Overlapping community detection model, including the partition density and fuzzy modularity metrics for community detection

Update Notifications





Write a Review

User Reviews

Be the first to post a review of Community Detection Modularity Suite!

Additional Project Details

Intended Audience

Science/Research

User Interface

Console/Terminal

Programming Language

C++, S/R

Registered

2012-02-20
Screenshots can attract more users to your project.
Features can attract more users to your project.

Icons must be PNG, GIF, or JPEG and less than 1 MiB in size. They will be displayed as 48x48 images.