KES 2007: Knowledge-Based Intelligent Information and Engineering Systems pp 413-420 | Cite as
Using Weak Prior Information on Structures to Learn Bayesian Networks
Abstract
Most of the approaches developed in the literature to elicit the a-priori distribution on Directed Acyclic Graphs (DAGs) require a full specification of graphs. Nevertheless, expert’s prior knowledge about conditional independence relations may be weak, making the elicitation task troublesome. Moreover, the detailed specification of prior distributions for structural learning is NP-Hard, making the elicitation of large networks impractical. This is the case, for example, of gene expression analysis, in which a small degree of graph connectivity is a priori plausible and where substantial information may regard dozens against thousands of nodes. In this paper we propose an elicitation procedure for DAGs which exploits prior knowledge on network topology, and that is suited to large Bayesian Networks. Then, we develop a new quasi-Bayesian score function, the P-metric, to perform structural learning following a score-and-search approach.
Keywords
Prior information structural learning Bayesian NetworksPreview
Unable to display preview. Download preview PDF.
References
- 1.Jensen, F.V.: An introduction to Bayesian Networks. Springer, Heidelberg New York (1996)Google Scholar
- 2.Chickering, D.M.: Learning Bayesian Networks is NP-Complete. In: Proceedings on Artificial Intelligence and Statistics, pp. 121–130 (1995)Google Scholar
- 3.Heckerman, D., Geiger, D., Chickering, D.M.: Learning Bayesian Network: A combination of knowledge and statistical data. In: Proceedings of 10th Conf. Uncertainty in Artificial Intelligence, pp. 293–301 (1994)Google Scholar
- 4.Heckerman, D., Meek, C., Cooper, G.: A Bayesian Approach to Causal Discovery. Technical Report MSR-TR-97-05. Microsoft Corporation, Redmond, WA (1997)Google Scholar
- 5.Buntine, W.L.: Theory of Refinement on Bayesian Networks. In: Proceedings of 7th Conference on Uncertainty in Artificial Intelligence, pp. 52–60 (1991)Google Scholar
- 6.Chickering, D.M., Geiger, D., Heckerman, D.: Learning Bayesian Network: A combination of knowledge and statistical data. Tecnical Report MSR-TR-94-17, Microsoft Research, Advanced Technology Division (1994)Google Scholar
- 7.Larrañaga, P., Poza, M.: Learning of Bayesian Networks by Genetic Algorithms: A Performance Analysis of Control Parameters IEEE. Journal on Pattern Analysis and Machine Intelligence 18(9), 912–926 (1996)CrossRefGoogle Scholar
- 8.Kullback, S., Leibler, R.A.M.: On Information and Sufficiency. Annals of Mathematical Statistics 22, 79–86 (1951)Google Scholar
- 9.Mascherini, M., Mastino: A Suite of R Functions to learn Bayesian Networks from data. UseR! International Conference of R Users, Vienna (Austria) (2006)Google Scholar
- 10.Bøttcher, S.G., Dethlefsen, C.: DEAL: A package for Learning Bayesian Networks. Journal of Statistical Software 8(20), 1–40 (2003)Google Scholar
- 11.Lauritzen, S.L., Spiegehalter, D.J.: Local Computation with probabilities on graphical structures and their application to expert system. Journal of the Royal Statistical Society - B Series 50(2), 157–192 (1988)MATHGoogle Scholar
- 12.Le, P.P., Bahl, A., Ungar, L.H.: Using prior knowledge to improve genetic network reconstruction from microarray data. InSilico Biology 27(4) (2004)Google Scholar