Detecting Network Communities: a new systematic and efficient algorithm

TL;DR

This paper introduces a new spectral and hierarchical clustering algorithm for detecting communities in complex networks, demonstrating comparable or superior speed and accuracy to existing methods across various network types.

Contribution

The paper presents a novel, efficient algorithm combining spectral graph theory and hierarchical clustering for community detection, with a modularity maximization procedure.

Findings

Performs at least as well as existing methods in accuracy.

Generally faster than comparable algorithms.

Effective on both synthetic and real-world networks.

Abstract

An efficient and relatively fast algorithm for the detection of communities in complex networks is introduced. The method exploits spectral properties of the graph Laplacian-matrix combined with hierarchical-clustering techniques, and includes a procedure to maximize the ``modularity'' of the output. Its performance is compared with that of other existing methods, as applied to different well-known instances of complex networks with a community-structure: both computer-generated and from the real-world. Our results are in all the tested cases, at least, as good as the best ones obtained with any other methods, and faster in most of the cases than methods providing similar-quality results. This converts the algorithm in a valuable computational tool for detecting and analyzing communities and modular structures in complex networks.