MCMC Louvain for Online Community Detection
Social and Information Networks
2016-12-06 v1 Physics and Society
Machine Learning
Abstract
We introduce a novel algorithm of community detection that maintains dynamically a community structure of a large network that evolves with time. The algorithm maximizes the modularity index thanks to the construction of a randomized hierarchical clustering based on a Monte Carlo Markov Chain (MCMC) method. Interestingly, it could be seen as a dynamization of Louvain algorithm (see Blondel et Al, 2008) where the aggregation step is replaced by the hierarchical instrumental probability.
Cite
@article{arxiv.1612.01489,
title = {MCMC Louvain for Online Community Detection},
author = {Yves Darmaillac and Sébastien Loustau},
journal= {arXiv preprint arXiv:1612.01489},
year = {2016}
}
Comments
12 pages, in progress, experiments are coming