A multiobjective evolutionary algorithm to find community structures based on affinity propagation

摘要: Community detection plays an important role in reflecting and understanding the topological structure of complex networks, can be used to help mine potential information networks. This paper presents a Multiobjective Evolutionary Algorithm based on Affinity Propagation (APMOEA) which improves accuracy community detection. Firstly, APMOEA takes method affinity propagation (AP) initially divide network. To accelerate its convergence, multiobjective evolutionary algorithm selects nondominated solutions from preliminary partitioning results as initial population. Secondly, finds approximating true Pareto optimal front through constantly selecting population after crossover mutation iterations, overcomes tendency data clustering methods fall into local optima. Finally, uses elitist strategy, called “external archive”, prevent degeneration during process searching using algorithm. According this obtained by AP will archived participate final selection Pareto-optimal solutions. Experiments benchmark test data, including both computer-generated networks eight real-world show that proposed achieves more accurate has faster convergence speed compared with seven other state-of-art algorithms.