Dependence discovery in modular Bayesian networks

This paper introduces an information theoretic approach to verification of modular causal probabilistic models. We assume systems which are gradually extended by adding new functional modules, each having a limited domain knowledge captured by a local Bayesian network. Different modules originate from independent design processes. We assume that the local models are correct, which, however does not guarantee globally coherent inference in composed systems. The introducedm ethod supports discovery of significant inter-module dependencies which are not captured in the assembled Bayesian network. We demonstrate the principles on a modularized gas detection fusion network.