Complex Network Community Detection based on Genetic Algorithm using K-cliques

Abstract

Inspired by the genetic algorithm, this paper proposes a complex network community detection algorithm, which searches for complete sub-graphs in a network, the numbers of nodes are greater than or equal to k, also referred to maximum k-cliques. K-cliques are the most connected communities in a network. Using the maximum k-clique initializes the population, which can improve the accuracy and efficiency of population initialization. K-clique-based population initialization, crossover, mutation, μ+λ selection strategy, and evaluation function (Q function) are adopted to select the next generation of population, the superior traits formed by parents during the process of evolution cannot be destroyed and can also be effectively inherited by offspring individuals. Finally, community partition is optimized using the fast Newman algorithm. This step performs further clustering on the communities. The algorithm can reduce the search space of community partition and improve the search efficiency of the algorithm. It is tested on benchmark networks and real-world networks. The algorithm has an acceptable time complexity. The experimental results show that the algorithm can effectively divide the communities.