The objective of this chapter is to connect the concepts of conditional independence with the separation in graphs. Both can be represented by a ternary relation Open image in new window on either the set of attributes or nodes and it seems to be promising to investigate how to represent the probabilistic properties of a distribution by the means of a graph. The idea then is to use only graph-theoretic criteria (separations) to draw inferences about (conditional) independences because it is them what enables us to decompose a high-dimensional distribution and propagate evidence.
- J. Gebhardt, H. Detmer, and A.L. Madsen. Predicting Parts Demand in the Automotive Industry—An Application of Probabilistic Graphical Models. Proc. Bayesian Modelling Applications Workshop at Int. Joint Conf. on Uncertainty in Artificial Intelligence (UAI 2003, Acapulco, Mexico), 2003 Google Scholar
- J. Gebhardt, A. Klose, H. Detmer, F. Rügheimer, and R. Kruse. Graphical Models for Industrial Planning on Complex Domains. In: D. Della Riccia, D. Dubois, R. Kruse, and H.-J. Lenz (eds.) Decision Theory and Multi-Agent Planning, CISM Courses and Lectures 482:131–143. Springer-Verlag, Berlin, Germany, 2006 CrossRefGoogle Scholar
- J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo, CA, USA, 1988 Google Scholar
- J. Pearl and A. Paz. Graphoids: A Graph Based Logic for Reasoning About Relevance Relations. In: B.D. Boulay, D. Hogg, and L. Steels (eds.) Advances in Artificial Intelligence 2, 357–363. North Holland, Amsterdam, Netherlands, 1987 Google Scholar