Community Detection Using Cooperative Co-evolutionary Differential Evolution

What is it about?

In many scientific fields, from biology to sociology, community detection in complex networks has become increasingly important. This paper proposes a novel algorithm, Cooperative Co-evolutionary Differential Evolution based Community Detection (CCDECD), based on the Cooperative Co-evolution framework for detecting communities in complex networks. CCDECD uses network modularity as the fitness function to search for an optimal partition of a network. A Bias Grouping scheme is proposed to dynamically decompose a complex network into smaller subnetworks to handle large-scale networks. We also designed a novel mutation operator specifically for community detection. CCDECD is evaluated on 5 small to large scale real-world social and biological networks. Experimental results show that CCDECD has a very competitive performance compared with other state-of-the-art community detection algorithms.

Featured Image

Photo by Austin Distel on Unsplash

Photo by Austin Distel on Unsplash

Why is it important?

This paper, for the first time, introduced the Cooperative Co-evolution Differential Evolution algorithm to detect community structure in complex networks. We have proposed the Bias Grouping scheme to dynamically decompose the complex network into smaller subcomponents for independent and co-adaptive evolution. We have also designed the global network mutation operator specifically for community detection problems, exploiting network connectivity information.

Perspectives