Predicting the Robustness of Large Real-World Social Networks Using a Machine Learning Model

Computing the robustness of a network, i.e., the capacity of a network holding its main functionality when a proportion of its nodes/edges are damaged, is useful in many real applications. The Monte Carlo numerical simulation is the commonly used method to compute network robustness. However, it has a very high computational cost, especially for large networks. Here, we propose a methodology such that the robustness of large real-world social networks can be predicted using machine learning models, which are pretrained using existing datasets. We demonstrate this approach by simulating two effective node attack strategies, i.e., the recalculated degree (RD) and initial betweenness (IB) node attack strategies, and predicting network robustness by using two machine learning models, multiple linear regression (MLR) and the random forest (RF) algorithm. We use the classic network robustness metric R as a model response and 8 network structural indicators (NSI) as predictor variables and trained over a large dataset of 48 real-world social networks, whose maximum number of nodes is 265,000. We found that the RF model can predict network robustness with a mean squared error (RMSE) of 0.03 and is 30% better than the MLR model. Among the results, we found that the RD strategy has more efficacy than IB for attacking real-world social networks. Furthermore, MLR indicates that the most important factors to predict network robustness are the scale-free exponent alpha and the average node degree <k>. On the contrary, the RF indicates that degree assortativity a, the global closeness, and the average node degree <k> are the most important factors. This study shows that machine learning models can be a promising way to infer social network robustness.