Complexity Analysis and Variational Inference for Interpretation-based Probabilistic Description Logic
Fabio Cozman, Rodrigo Polastro
This paper presents complexity analysis and variational methods for inference in probabilistic description logics featuring Boolean operators, quantification, qualified number restrictions, nominals, inverse roles and role hierarchies. Inference is shown to be PEXP-complete, and variational methods are designed so as to exploit logical inference whenever possible.
PDF Link: /papers/09/p117-cozman.pdf
AUTHOR = "Fabio Cozman
and Rodrigo Polastro",
TITLE = "Complexity Analysis and Variational Inference for Interpretation-based Probabilistic Description Logic",
BOOKTITLE = "Proceedings of the Twenty-Fifth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-09)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2009",
PAGES = "117--125"