Using ROBDDs for Inference in Bayesian Networks with Troubleshooting as an Example

TL;DR

This paper explores using Reduced Ordered Binary Decision Diagrams (ROBDDs) to improve inference in Bayesian networks, especially for troubleshooting, by leveraging deterministic Boolean functions to speed up belief updating.

Contribution

It introduces a novel approach applying ROBDDs to Bayesian network inference, demonstrating significant speed improvements over traditional methods.

Findings

Substantial speed-up in belief updating using ROBDDs

Effective handling of deterministic parts in Bayesian networks

Experimental results outperform junction tree propagation

Abstract

When using Bayesian networks for modelling the behavior of man-made machinery, it usually happens that a large part of the model is deterministic. For such Bayesian networks deterministic part of the model can be represented as a Boolean function, and a central part of belief updating reduces to the task of calculating the number of satisfying configurations in a Boolean function. In this paper we explore how advances in the calculation of Boolean functions can be adopted for belief updating, in particular within the context of troubleshooting. We present experimental results indicating a substantial speed-up compared to traditional junction tree propagation.