Identification of network modules by optimization of ratio association

TL;DR

This paper presents a new method for detecting network modules by optimizing the ratio association, leveraging probabilistic autoencoders and kernel k-means analogies, with demonstrated effectiveness on real and simulated networks.

Contribution

It introduces a novel ratio association-based approach for network community detection, combining probabilistic autoencoder concepts with an efficient deterministic annealing optimization.

Findings

Effective detection of network modules demonstrated on real data

Method outperforms traditional clustering approaches

Applicable to both real and simulated networks

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.