Structured probabilistic inference

Probabilistic inference is among the main topics with reasoning in uncertainty in AI. For this purpose, Bayesian Networks (BNs) is one of the most successful and efficient Probabilistic Graphical Model (PGM) so far. Since the mid-90s, a growing number of BNs extensions have been proposed. Object-oriented, entity-relationship and first-order logic are the main representation paradigms used to extend BNs. While entity-relationship and first-order models have been successfully used for machine learning in defining lifted probabilistic inference, object-oriented models have been mostly underused. Structured inference, which exploits the structural knowledge encoded in an object-oriented PGM, is a surprisingly unstudied technique. In this paper we propose a full object-oriented framework for PRM and propose two extensions of the state-of-the-art structured inference algorithm: SPI which removes the major flaws of existing algorithms and SPISBB which largely enhances SPI by using d-separation.

► This paper presents new inference algorithms in Object-Oriented Bayesian Networks, based on Probabilistic Relational Models.
► After a survey, we present the version of PRMs used in this work.
► We then adapt state-of-the-art Structured Variable Elimination (SVE) algorithm to our framework.
► We show that some drawbacks of SVE can be removed in a new algorithm called SPI.
► In order to speed-up the inference, we include a d-separation analysis at class level, leading to a new algorithm SPISBB which outperforms other algorithms.