Robustness in Weighted Networks

In the last two decades, Network science has become a strategic field of research thanks to both the increased availability of large datasets, and the strong development of high-performance computing technologies and methodologies. Different types of data will produce different types of complex networks in terms of structure, connectivity, and complexity. Examples range from biology to business and from technology to sociology. A network is said to have a community structure if the nodes are densely connected within groups but sparsely connected between them (1). A number of methods for community detection have been proposed. However, their implementation leaves unaddressed the question of the statistical validation of the results. A first method to statistically test the robustness of undirected and unweighted networks was proposed in (2; 3). The method uses a configuration model as a null random model to test the hypothesis that the detected communities are due only to the random position of the edges in the graph. In this work we propose a Machine Learning approach to perform robustness analysis for weighted Networks.