Benchmarking dynamic Bayesian network structure learning algorithms

Dynamic Bayesian Networks (DBNs) are probabilistic graphical models dedicated to modeling multivariate time series. Two-time slice BNs (2-TBNs) are the most current type of these models. Static BN structure learning is a well-studied domain. Many approaches have been proposed and the quality of these algorithms has been studied over a range of di erent standard networks and methods of evaluation. To the best of our knowledge, all studies about DBN structure learning use their own benchmarks and techniques for evaluation. The problem in the dynamic case is that we don't find previous works that provide details about used networks and indicators of comparison. In addition, access to the datasets and the source code is not always possible. In this paper, we propose a novel approach to generate standard DBNs based on tiling and novel technique of evaluation, adapted from the "static" Structural Hamming Distance proposed for Bayesian networks