Reliable prediction in the Markov stochastic block model

We introduce the Markov Stochastic Block Model (MSBM): a growth model for community based networks where node attributes are assigned through Markovian dynamic. rely on HMMs’ literature to design prediction methods that robust local clustering errors. focus specifically link and collaborative filtering problems we new selection procedure infer number of hidden clusters in network. Our approaches reliable MSBMs not algorithm-dependent sense they can be applied using your favourite tool. In this paper, use recent SDP method communities provide theoretical guarantees. particular, identify relevant signal-to-noise ratio (SNR) our framework prove misclassification error decays exponentially fast with respect SNR.