Lifting Factor Graphs with Some Unknown Factors
Published in Seventeenth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, 2023
Malte Luttermann, Ralf Möller, Marcel Gehrke. (2023). "Lifting Factor Graphs with Some Unknown Factors." Proceedings of the Seventeenth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU-2023). Springer, Volume 14294, pages 337-347. https://link.springer.com/chapter/10.1007/978-3-031-45608-4_25
Abstract
Lifting exploits symmetries in probabilistic graphical models by using a representative for indistinguishable objects, allowing to carry out query answering more efficiently while maintaining exact answers. In this paper, we investigate how lifting enables us to perform probabilistic inference for factor graphs containing factors whose potentials are unknown. We introduce the Lifting Factor Graphs with Some Unknown Factors (LIFAGU) algorithm to identify symmetric subgraphs in a factor graph containing unknown factors, thereby enabling the transfer of known potentials to unknown potentials to ensure a well-defined semantics and allow for (lifted) probabilistic inference.
Resources for this Paper
BibTeX Citation
@inproceedings{Luttermann2023b,
author = {Malte Luttermann and Ralf M\"oller and Marcel Gehrke},
title = {{Lifting Factor Graphs with Some Unknown Factors}},
booktitle = {Proceedings of the Seventeenth European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU-2023)},
year = {2023},
pages = {337--347},
publisher = {Springer},
}