Belief Updating in Msbns without Repeated Local Propagations

We redeene inference operations for multiply sectioned Bayesian networks (MS-BNs). When two adjacent subnets exchange belief, previous operations require repeated belief propagations within the receiving subnet. The new operations require such propagation only twice. We prove that the new operations do not compromise the coherence while improving the eeciency. A MSBN must be initialized before inference can take place. The initialization involves special operations not shared by inference computation. We show that the new inference operations unify inference and initialization. Therefore, the new operations not only are more eecient, but also are simpler. They speed up inference as well as ease practical implementation.