Co-modularity and Detection of Co-communities

TL;DR

This paper proposes co-modularity, a new measure for co-clustering bipartite networks into co-communities, with applications demonstrated in genomics and consumer reviews.

Contribution

It introduces the concept of co-modularity for assessing and optimizing co-clusters in bipartite networks, a novel approach in network analysis.

Findings

Effective co-clustering demonstrated on simulated data

Application to genomics data shows biological relevance

Consumer review analysis reveals meaningful co-communities

Abstract

This paper introduces the notion of co-modularity, to co-cluster observations of bipartite networks into co-communities. The task of co-clustering is to group together nodes of one type with nodes of another type, according to the interactions that are the most similar. The novel measure of co-modularity is introduced to assess the strength of co-communities, as well as to arrange the representation of nodes and clusters for visualisation, and to define an objective function for optimisation. We demonstrate the usefulness of our proposed methodology on simulated data, and with examples from genomics and consumer-product reviews.