Detecting change points in dynamic networks by measuring cluster stability

Clustering patterns are ubiquitously present in a variety of networked systems, and may change with the evolution of network topology. Probing into the cluster structures can shed light on the change of the entire network, especially those sudden changes emerging in the process of network evolution. Though abundant researches have been done in detecting the changes of dynamic networks, more precisely, change points at which the network topology experiences abrupt changes, most of the existing methods focus on local changes (e.g. edges change) that are commonly mixed with noise, giving rise to high false positive reports. Different from the previous work, here we inspect the topological changes from mesoscale clusters of dynamic networks, which will reduce the perturbation of link variation to detection accuracy. Towards this end, we look for the invariant clusters of nodes during the observation window in dynamic networks and propose a new measure to quantify the stability of node clusters with respect to the invariant clustering patterns. Then the change of dynamic networks at mesoscale can be captured by comparing the variations of stability measures. In the light of the proposed measurement, we design a change-point detection algorithm and conduct extensive experiments on synthetic and real-life datasets to demonstrate the effectiveness of our method. The results show the outperformance of our method in identifying change points, compared to several baseline methods.