A new immunization algorithm based on spectral properties for complex networks

Nowadays, we are facing epidemic spreading in many different areas; examples are infection propagation, rumor spreading and computer viruses in computer networks. Finding a strategy to control and mitigate the spread of these epidemics is gaining much interest in recent researches. Due to limitation of immunization resources, it is important to establish a strategy for selecting nodes which has the most effect in mitigating epidemics. In this paper, we propose a new algorithm that minimizes the worst expected growth of an epidemic by reducing the size of the largest connected component of the underlying contact network. The proposed algorithm is applicable to any level of available resources and, despite the greedy approaches of most immunization strategies, selects nodes simultaneously. In each iteration, the proposed method partitions the largest connected component into two groups. These are the best candidates for communities in that component, and the available resources are sufficient to separate them. Using Laplacian spectral partitioning, the proposed method performs community detection inference with a time complexity that rivals that of the best previous methods. Experiments show that our method outperforms targeted immunization approaches in real networks.