Research On Community Detection Algorithm Based On Link Dynamics In Complex Networks

With the in-depth study of complex networks.,it is found that the community structure is a property shared by many of our real and real networks.The connections between nodes and nodes in the community are very close.Relatively speaking,the connection between the community and the community is relatively sparse.Revealing the community structure of the network is important for understanding the network structure and analyzing the network characteristics.Discovery of communities in complex networks is a fundamental data analysis problem with applications in various domains.Most of the existing approaches have focused on discovering communities of nodes,while recent studies have shown great advantages and utilities of the knowledge of communities of links in networks.From this new perspective,we propose an algorithm based on link dynamics,called LDA,which can effectively detect the link community in the network.The key idea behind LDA lies in the connection between the community structure of the network and some attributes of the link dynamic process of random walk.Based on this,we can divide the network edge into two separable parts.Specifically,the new algorithm operates in two phases of iteration and recursion:the first phase of LDA reveals the bipartite structure of the network by evaluating the transition probability distribution of the random process(aggregated)of the link-node-link random walk;Next,the two link modules appearing in the first stage of LDA are extracted by the LDA second-stage subroutine,which utilizes the local mixed attributes hidden in the markov chain of the random process above.An iterative process is introduced to recursively subdivide the network structure to produce an integrated LDA algorithm.This algorithm is very effective in finding synthetic benchmark and some link community structure of real network.LDA can also be extended to effectively extract node communities on some real-world networks.