A Graph-Based Inference Method for Conditional Independence
The graphoid axioms for conditional independence, originally described by Dawid , are fundamental to probabilistic reasoning [Pearl, 19881. Such axioms provide a mechanism for manipulating conditional independence assertions without resorting to their numerical definition. This paper explores a representation for independence statements using multiple undirected graphs and some simple graphical transformations. The independence statements derivable in this system are equivalent to those obtainable by the graphoid axioms. Therefore, this is a purely graphical proof technique for conditional independence.
PDF Link: /papers/91/p353-shachter.pdf
AUTHOR = "Ross Shachter
TITLE = "A Graph-Based Inference Method for Conditional Independence",
BOOKTITLE = "Proceedings of the Seventh Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-91)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Mateo, CA",
YEAR = "1991",
PAGES = "353--360"