Title :
A community clustering algorithm based on genetic algorithm with novel coding scheme
Author :
Xianghua Li ; Chao Gao ; Ruyang Pu
Author_Institution :
Coll. of Comput. & Inf. Sci., Southwest Univ., Chongqing, China
Abstract :
Community structure is one of the basic characteristics of a complex network, which plays an important role in the function of a network. According to the premature convergence of traditional genetic algorithm on community detection, this paper proposes a new coding scheme based on the attribute partition of edges. The new strategy is named as NGACD. Each nonzero gene in the NGACD represents the attribute partition between two nodes. Based on the novel coding scheme, NGACD is feasible for crossover and mutation operations. Specifically, the NGACD is independent of the context and exhibits the more features of modularity. Four benchmark network are used to estimate the efficiency of proposed strategy. The simulation results show that our algorithm is more accurate and stable than others.
Keywords :
convergence; data structures; genetic algorithms; graph theory; network theory (graphs); pattern clustering; NGACD strategy; benchmark network; coding scheme; community clustering algorithm; community detection; community structure; complex network characteristics; convergence; crossover operation; edge attribute partitioning; efficiency estimation; genetic algorithm; modularity features; mutation operation; network function; nonzero gene; Benchmark testing; Communities; Convergence; Encoding; Genetic algorithms; Sociology; Statistics; Complex networks; attribute partition; community detection; genetic algorithm;
Conference_Titel :
Natural Computation (ICNC), 2014 10th International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4799-5150-5
DOI :
10.1109/ICNC.2014.6975883