Memetic algorithm using node entropy and partition entropy for community detection in networks

Community detection is a key to understanding the structure of complex networks. Many community detection approaches have been proposed based on the modularity optimization. Algorithms that optimize one initial solution often get into local optima, but algorithms that simultaneously optimize a population of solutions have high computational complexity. To solve these problems, genetic algorithms improved by a local learning procedure known as memetic algorithms can be applied. We propose a memetic algorithm for community detection in networks, that exploits node entropy for local learning. Node entropy is easy to use to speed up the convergence of an evolutionary algorithm and to increase the quality of partitions, while it uses only the node's neighborhood and does not require any threshold value. Moreover, this algorithm is slightly modified in order to avoid modularity function which suffers a resolution limit and, therefore, it may fail to detect small communities. We propose and use an entropy function as an optimization function and as criteria in grouping crossover operator. Experiments on real-world and synthetic networks illustrate that the proposed method can find natural partitions effectively.