FLIP-CPM: A Parallel Community Detection Method

Uncovering the underlying community structure of networks modelling real-world complex systems is essential way to gain insight both into their structure and their functional organization. Of all the definitions of community proposed by researchers, we focused on the k-clique community definition as we believe it best catches the characteristics of many real networks. Currently, extracting k-clique communities using the methods available in the literature requires a formidable amount of computational load and memory resources. In this paper we propose a new parallel method that has proved its capability in extracting k-clique communities efficiently and effectively from some real-world complex networks for which these communities had never been detected before. This innovative method is much less resource intensive than Clique Percolation Method and experimental results show it is always at least an order of magnitude faster. In addition, tests run on parallel architectures show a noticeable speedup factor, in some cases linear with the number of cores.