MODULARITY MAXIMIZATION FOR COMMUNITY DETECTION IN NETWORKS USING COMPETITIVE HOPFIELD NEURAL NETWORK

摘要

Community detection finds its applications in the biological networks and social networks, like predicting functional modules of proteins, recommending items to the users based on their interests, and exploring potential relationships among persons. Modularity is a widely-used criterion for evaluating the quality of the detected community structures. Due to the NP-hard property of modularity maximization, developing the approximate algorithms with good accuracy and computational complexity is challenging and of great significance. In this paper, a novel algorithm based on competitive Hopfield neural network (CHNN for short) for maximizing modularity is proposed, where a new energy function and a two-dimensional topology are designed, and the winner-takes-all strategy for updating the outputs of neurons in each row of CHNN is adopted. Moreover, the convergence of the proposed algorithm is proved. The algorithm is capable of converging fast and achieving good modularity. Experimental results on multiple empirical and synthetic networks show the proposed algorithm can effectively and efficiently identify the community structures of the networks, and has the competitive performance compared to several other baseline algorithms for community detection.