|
Abstract:
|
Many models and methods are now available for network analysis, but model selection and tuning remain challenging. Cross-validation is a useful general tool for these tasks in many settings, but is not directly applicable to networks since splitting network nodes into groups requires deleting edges and destroys some of the network structure. We propose a new edge sampling cross-validation strategy applicable to a wide range of network problems. We provide an error bound on cross-validated estimates in a general setting, and in particular show that the method has good asymptotic properties when selecting the number of communities under the stochastic block model. Numerical results on both simulated and real networks show that our approach performs well for a number of model selection and tuning parameter tasks.
|
