Detecting Overlapping Link Communities by Finding Local Minima of a Cost Function with a Memetic Algorithm. Part 1: Problem and Method

TL;DR

This paper introduces a memetic algorithm for detecting overlapping link communities in networks, utilizing a novel cost function and local information to handle pervasive overlaps, with experimental results to follow.

Contribution

It presents a new algorithm combining evolutionary strategies and local search for link community detection with overlapping communities.

Findings

Algorithm effectively detects overlapping communities.

Utilizes a new evaluation function for community quality.

Applicable to citation networks in experiments.

Abstract

We propose an algorithm for detecting communities of links in networks which uses local information, is based on a new evaluation function, and allows for pervasive overlaps of communities. The complexity of the clustering task requires the application of a memetic algorithm that combines probabilistic evolutionary strategies with deterministic local searches. In Part 2 we will present results of experiments with with citation networks.