Robustness of centrality measures against network manipulation

Node centrality is an important quantity to consider in studying complex networks as it is related to many applications ranging from the prediction of network structure to the control of dynamics on networks. In the literature, much effort has been devoted to design new centrality measurements. However, the reliability of these centrality measurements has not been fully assessed, particularly with respect to the fact that many real networks are facing different kinds of manipulations such as addition, removal or rewiring of links. In this paper, we focus on the robustness of classic centrality measures against network manipulation. Our analysis is based on both artificial and real networks. We find that the centrality measurements are generally more robust in heterogeneous networks. Biased link manipulation could more seriously distort the centrality measures than random link manipulation. Moreover, the top part of the centrality ranking is more resistant to manipulation. (C) 2015 Elsevier B.V. All rights reserved.