Population Learning Based Memetic Algorithm for Community Detection in Complex Networks

Abstract

Community structure property is indispensable to discover the potential functionality of complex systems. Community detection (community discovery) is a technology for revealing the behavior of nodes aggregation in complex networks. To uncover the community structure of networks in a fast and effective way, in this paper, we propose a novel memetic algorithm called memetic algorithm with population learning (MAPL) based on the optimization of modularity. The proposed MAPL consists of a new initialization method, which can improve the population quality and accelerate the convergence of the algorithm to the optimal solutions, genetic operations and a local search using population learning to guide the direction of the optimization process. Extensive experiments on both synthetic networks and real-world networks demonstrate that compared with the five classic algorithms, the proposed MAPL has effective performance on discovering the community structure of complex networks.