Clusters from higher order correlations

TL;DR

This paper introduces a novel clustering method for variables that leverages higher-order correlations using a Potts model and Monte Carlo simulations, effectively capturing complex relationships in biological and other systems.

Contribution

The paper presents a new approach that utilizes higher-order correlations through a Potts model and Monte Carlo methods to improve variable clustering accuracy.

Findings

Higher-order correlations improve clustering accuracy in biological systems.

The method successfully identifies clusters in complex systems.

Significant third-order correlations enhance clustering results.

Abstract

Given a set of variables and the correlations among them, we develop a method for finding clustering among the variables. The method takes advantage of information implicit in higher-order (not just pairwise) correlations. The idea is to define a Potts model whose energy is based on the correlations. Each state of this model is a partition of the variables and a Monte Carlo method is used to identify states of lowest energy, those most consistent with the correlations. A set of the 100 or so lowest such partitions is then used to construct a stochastic dynamics (using the adjacency matrix of each partition) whose observable representation gives the clustering. Three examples are studied. For two of them the 3$^\mathrm{rd}$ order correlations are significant for getting the clusters right. The last of these is a toy model of a biological system in which the joint action of several genes or proteins is necessary to accomplish a given process.