zhuloucao/communitydetection

Community detection in graphs (Stochastic block model, Bethe Hessian, Spectral clustering)

CommunityDetection

Community detection in graphs/networks project

Stochastic block model implementation, spectral clustering with the bethe hessian and comparison with other methods (adjacency matrix, Laplacian matrix, modularity matrix)

Stochastic block model

From Wikipedia:

The stochastic block model takes the following parameters:

• The number n of vertices
• a partition of the vertex set {1, ..., n} into disjoint subsets {C1, ..., Cr} called communities
• a symmetric r x r matrix P of edge probabilities. The edge set is then sampled at random as follows: any two vertices u in Ci and v in Cj are connected by an edge with probability Pij.

Bethe Hessian matrix

arXiv.org

Spectral clustering

Wikipedia

Requirements

• Python 2.7
• Networkx
• Numpy
• Sklearn
• Scipy