Lifted First-Order Probabilistic Inference
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1319-1324.
Abstract
Most probabilistic inference algorithms are specified and processed on a propositional level. In the last decade, many proposals for algorithms accepting first-order specifications have been presented, but in the inference stage they still operate on a mostly propositional representation level. [Poole, 2003] presented a method to perform inference directly on the first-order level, but this method is limited to special cases. In this paper we present the first exact inference algorithm that operates directly on a first-order level, and that can be applied to any first-order model (specified in a language that generalizes undirected graphical models). Our experiments show superior performance in comparison with propositional exact inference.
@inproceedings{ijcai2005p204,
title = {Lifted First-Order Probabilistic Inference},
author = {Braz, Rodrigo de Salvo and Amir, Eyal and Roth, Dan},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {1319--1324},
year = {2005},
url = {https://ijcai.org/proceedings/2005/204},
}
TY - CPAPER TI - Lifted First-Order Probabilistic Inference AU - Braz, Rodrigo de Salvo AU - Amir, Eyal AU - Roth, Dan T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 1319 EP - 1324 UR - https://ijcai.org/proceedings/2005/204 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
