FCA-based θ-iceberg core decomposition in graphs

Fei Hao, Khamphaphone Xinchang, Doo-Soon Park

Abstract: Complex networking analysis is a powerful technique for understanding both complex networks and big graphs in ubiquitous computing. Particularly, there are several novel metrics, such as k-clique and k-core are proposed in order to study the relative importance of nodes in complex networks. Among of those metrics, k-core analysis is an effective approach for simplifying graphical structure. However, the relation between k and the scale of networks is not explored in most existing literature. Toward this end, this paper formulate a new research problem, \(\theta\)-Iceberg Core decomposition in graphs, which is able to incorporate a parameter \(\theta\) (\(0<\theta \le 1\)) used for relaxing the output of k-cores. Further, we propose a formal concept analysis based approach for \(\theta\)-Iceberg Core decomposition. The proposed approach and its conclusions can provide theoretical basis and guidance for the potential applications of \(\theta\)-Iceberg Core analysis in complex networks.