An ensemble based on a bi-objective evolutionary spectral algorithm for graph clustering

TL;DR

This paper presents MOSpecG, a hybrid spectral and evolutionary algorithm with an ensemble approach for graph clustering, achieving improved community detection results on real and artificial networks.

Contribution

It introduces a novel bi-objective spectral evolutionary algorithm with an ensemble strategy for robust graph clustering, outperforming existing methods.

Findings

Significant improvement over previous bi-objective algorithms.

The geometric crossover operator enhances community matching.

High-quality community structures are achieved through hybridization.

Abstract

Graph clustering is a challenging pattern recognition problem whose goal is to identify vertex partitions with high intra-group connectivity. This paper investigates a bi-objective problem that maximizes the number of intra-cluster edges of a graph and minimizes the expected number of inter-cluster edges in a random graph with the same degree sequence as the original one. The difference between the two investigated objectives is the definition of the well-known measure of graph clustering quality: the modularity. We introduce a spectral decomposition hybridized with an evolutionary heuristic, called MOSpecG, to approach this bi-objective problem and an ensemble strategy to consolidate the solutions found by MOSpecG into a final robust partition. The results of computational experiments with real and artificial LFR networks demonstrated a significant improvement in the results and performance of the introduced method in regard to another bi-objective algorithm found in the literature. The crossover operator based on the geometric interpretation of the modularity maximization problem to match the communities of a pair of individuals was of utmost importance for the good performance of MOSpecG. Hybridizing spectral graph theory and intelligent systems allowed us to define significantly high-quality community structures.