Workload-aware materialization for efficient variable elimination on Bayesian networks

Cigdem Aslay, Martino Ciaperoni, Aristides Gionis, Michael Mathioudakis

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Bayesian networks are general, well-studied probabilistic models that capture dependencies among a set of variables. Variable Elimination is a fundamental algorithm for probabilistic inference over Bayesian networks. In this paper, we propose a novel materialization method, which can lead to significant efficiency gains when processing inference queries using the Variable Elimination algorithm. In particular, we address the problem of choosing a set of intermediate results to precompute and materialize, so as to maximize the expected efficiency gain over a given query workload. For the problem we consider, we provide an optimal polynomial-time algorithm and discuss alternative methods. We validate our technique using real-world Bayesian networks. Our experimental results confirm that a modest amount of materialization can lead to significant improvements in the running time of queries, with an average gain of 70%, and reaching up to a gain of 99%, for a uniform workload of queries. Moreover, in comparison with existing junction tree methods that also rely on materialization, our approach achieves competitive efficiency during inference using significantly lighter materialization.
Original languageEnglish
Title of host publicationIEEE International Conference on Data Engineering (ICDE)
Publication statusAccepted/In press - 25 Mar 2021
MoE publication typeA4 Article in conference proceedings

Cite this