Identification of network modules by optimization of ratio association
Disordered Systems and Neural Networks
2009-11-11 v2
Abstract
We introduce a novel method for identifying the modular structures of a network based on the maximization of an objective function: the ratio association. This cost function arises when the communities detection problem is described in the probabilistic autoencoder frame. An analogy with kernel k-means methods allows to develop an efficient optimization algorithm, based on the deterministic annealing scheme. The performance of the proposed method is shown on a real data set and on simulated networks.
Keywords
Cite
@article{arxiv.cond-mat/0610182,
title = {Identification of network modules by optimization of ratio association},
author = {Leonardo Angelini and Stefano Boccaletti and Daniele Marinazzo and Mario Pellicoro and Sebastiano Stramaglia},
journal= {arXiv preprint arXiv:cond-mat/0610182},
year = {2009}
}