Inference in Multiply Sectioned Bayesian Networks with Extended Shafer-Shenoy and Lazy Propagation

TL;DR

This paper combines multiply sectioned Bayesian networks with lazy propagation techniques to enhance inference efficiency and scalability in large, complex domains, enabling exact inference with reduced space complexity.

Contribution

It introduces the integration of lazy propagation with MSBNs, improving inference efficiency and scalability in large Bayesian network models.

Findings

Reduces space complexity of inference in MSBNs

Enables exact inference in larger domains

Retains modeling flexibility of MSBNs

Abstract

As Bayesian networks are applied to larger and more complex problem domains, search for flexible modeling and more efficient inference methods is an ongoing effort. Multiply sectioned Bayesian networks (MSBNs) extend the HUGIN inference for Bayesian networks into a coherent framework for flexible modeling and distributed inference.Lazy propagation extends the Shafer-Shenoy and HUGIN inference methods with reduced space complexity. We apply the Shafer-Shenoy and lazy propagation to inference in MSBNs. The combination of the MSBN framework and lazy propagation provides a better framework for modeling and inference in very large domains. It retains the modeling flexibility of MSBNs and reduces the runtime space complexity, allowing exact inference in much larger domains given the same computational resources.