Title: DMRFO-CD: a discrete manta ray foraging inspired optimisation algorithm for community detection in networks

Authors: Priyanka Gupta; Shikha Gupta; Naveen Kumar

Addresses: Mata Sundri College for Women, Department of Computer Science, University of Delhi, Delhi, India ' Shaheed Sukhdev College of Business Studies, Department of Computer Science, University of Delhi, Delhi, India ' Department of Computer Science, University of Delhi, Delhi, India

Abstract: There has been considerable interest in using bio-inspired evolutionary algorithms to detect communities in networks. Manta ray foraging optimisation (MRFO), a recently proposed real-valued bio-inspired evolutionary algorithm, has demonstrated superior performance in challenging complex optimisation problems. The present proposal is significant in its adaptation of the MRFO algorithm for the discrete-valued community detection problem. The proposed approach leverages the strengths of the MRFO algorithm for superior results through better exploration of the search space. The proposed approach maximises network modularity, a measure of connection density within a community. Higher modularity community structures find usefulness in uncovering meaningful information in the network. Experiments on real-world and synthetic benchmark networks show that the proposed approach successfully detects community structures with high modularity. We experimented on both real-world and synthetic benchmark networks. In two-thirds of the cases, the proposed algorithm achieved a higher modularity. For the remaining networks, the modularity achieved by the proposed approach was the same as that of the label.

Keywords: evolutionary algorithms; network modularity; normalised mutual information; metaheuristic; swarm-based; partitioning.

DOI: 10.1504/IJCSE.2024.142838

International Journal of Computational Science and Engineering, 2024 Vol.27 No.6, pp.718 - 733

Received: 05 Mar 2023
Accepted: 22 Jan 2024
Published online: 28 Nov 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article