A novel community detection algorithm based on clonal selection

According to the framework of artificial immune system (AIS), this paper constructs the mapping between community detection in a complex network and AIS. Then we propose a novel community detection algorithm based on the immune clonal selection principle to govern the system. In order to detect the community structure of a network that is considered as Ag data (antigen), there are three basic elements in our algorithm: Bm data (memory B cell), APC data (antigen presenting cell) and Bc data (B cell) that containing Ab data (antibody). The affinity between Ag data and Ab data is estimated by modularity Q. Through the clonal selection, Bm data keeps the optimal solution for a network. Some real-world networks are used to compare our algorithm with some typical community detection algorithms. Experimental results show that our algorithm can obtain more scalable and accurate solution with a lower computational cost.