Multi-objective Evolutionary Algorithm based on Ensemble of Initializations for Overlapping Community Detection

Recently, developing efficient multi-objective evolutionary algorithms (MOEAs) for detect communities in complex networks has received immense recognition. Employing MOEAs for community detection provide a set of Pareto-optimal solutions (PS) where each solution in PS represent different network partition. In literature, majority of existing approaches proposed for detecting community structures focus on obtaining disjoint communities (each node belongs to a unique community). However, communities in real-world networks often overlap with each other and thus it is essential to develop algorithms for overlapping community detection. Hence, in this paper, we propose a MOEA based on ensemble of initializations for overlapping community detection (OCD-enMOEA). In OCD-enMOEA, we employ an ensemble of initialization procedure, where the individuals are encoded by an indirect representation based on permutation. Then, a decoding procedure based on community fitness is employed to transform the individuals into communities. The community fitness metrics adopted for decoding is associated with a resolution parameter α, which allows exploration of community structures at different levels of granularity. However, the community fitness metric is very sensitive to the parameter α and adapting the parameter to achieve better performance is very difficult. Hence, in this paper, we employ a set of values for the parameter α as an ensemble and transform the individuals into communities. To validate the performance of proposed OCD-enMOEA, we have employed five real-world networks and compared with six baseline algorithms to detect overlapping communities. The experimental results demonstrate that the proposed method exhibit better performance in comparison with the baseline algorithms.