Identifying Independence in Relational Models
Artificial Intelligence
2013-04-16 v3
Abstract
The rules of d-separation provide a framework for deriving conditional independence facts from model structure. However, this theory only applies to simple directed graphical models. We introduce relational d-separation, a theory for deriving conditional independence in relational models. We provide a sound, complete, and computationally efficient method for relational d-separation, and we present empirical results that demonstrate effectiveness.
Cite
@article{arxiv.1206.3536,
title = {Identifying Independence in Relational Models},
author = {Marc Maier and David Jensen},
journal= {arXiv preprint arXiv:1206.3536},
year = {2013}
}
Comments
This paper has been revised and expanded. See "Reasoning about Independence in Probabilistic Models of Relational Data" http://arxiv.org/abs/1302.4381