Date of Award


Publication Type

Master Thesis

Degree Name



Computer Science


Artificial intelligence, Bayesian network, Probabilistic inference, Junction tree, Probability Propagation, Reasoning under uncertainty


Dan Wu




Many researches have been done for efficient computation of probabilistic queries posed to Bayesian networks (BN). One of the popular architectures for exact inference on BNs is the Junction Tree (JT) based architecture. Among all the different architectures developed, HUGIN is the most efficient JT-based architecture. The Global Propagation (GP) method used in the HUGIN architecture is arguably one of the best methods for probabilistic inference in BNs. Before the propagation, initialization is done to obtain the potential for each cluster in the JT. Then with the GP method, each cluster potential becomes cluster marginal through passing messages with its neighboring clusters. Improvements have been proposed by many researchers to make this message propagation more efficient. Still the GP method can be very slow for dense networks. As BNs are applied to larger, more complex, and realistic applications, developing more efficient inference algorithm has become increasingly important. Towards this goal, in this paper, we present some heuristics for initialization that avoids unnecessary message passing among clusters of the JT and therefore it improves the performance of the architecture by passing lesser messages.