Extended Lifted Inference with Joint Formulas
This work addresses a bottleneck in exact inference for probabilistic relational models, offering incremental improvements for researchers in AI and decision-making under uncertainty.
The paper tackles the limited applicability of the First-Order Variable Elimination (FOVE) algorithm in probabilistic relational models by introducing two new model conversion operators, enabling efficient inference where previously impossible and extending it to solve Maximum Expected Utility queries. Experimental results demonstrate significant speedup over existing alternatives.
The First-Order Variable Elimination (FOVE) algorithm allows exact inference to be applied directly to probabilistic relational models, and has proven to be vastly superior to the application of standard inference methods on a grounded propositional model. Still, FOVE operators can be applied under restricted conditions, often forcing one to resort to propositional inference. This paper aims to extend the applicability of FOVE by providing two new model conversion operators: the first and the primary is joint formula conversion and the second is just-different counting conversion. These new operations allow efficient inference methods to be applied directly on relational models, where no existing efficient method could be applied hitherto. In addition, aided by these capabilities, we show how to adapt FOVE to provide exact solutions to Maximum Expected Utility (MEU) queries over relational models for decision under uncertainty. Experimental evaluations show our algorithms to provide significant speedup over the alternatives.