Query the model: precomputations for efficient inference with Bayesian Networks

TL;DR

This paper introduces a novel materialization technique for Variable Elimination in Bayesian networks, significantly improving inference efficiency with minimal precomputations, and offers a competitive alternative to junction tree methods.

Contribution

It presents a new materialization method for Variable Elimination that enhances inference speed with less precomputation compared to existing junction tree approaches.

Findings

Materialization improves inference query times substantially.

The proposed method achieves comparable efficiency to junction tree methods.

Lightweight precomputations are sufficient for significant performance gains.

Abstract

Variable Elimination is a fundamental algorithm for probabilistic inference over Bayesian networks. In this paper, we propose a novel materialization method for Variable Elimination, which can lead to significant efficiency gains when answering inference queries. We evaluate our technique using real-world Bayesian networks. Our results show that a modest amount of materialization can lead to significant improvements in the running time of queries. Furthermore, in comparison with junction tree methods that also rely on materialization, our approach achieves comparable efficiency during inference using significantly lighter materialization.