Mapping and parallel implementation of Bayesian belief networks

Abstract

Presents an efficient technique for mapping arbitrarily large Bayesian belief networks on hypercubes with deadlock-free implementation. We show that the speedup does not vary with the number of nodes in the Bayesian network and is limited by the height of the Peot-Shachter tree which is obtained by hanging the Bayesian polytree by a pivot node. We also found that the overhead in implementing Bayesian networks on parallel machines like hypercubes can be large because of the communication intensive nature of the network.