Abstract
The K2 metric is a well-known evaluation measure (or scor-ing function) for learning Bayesian networks from data [7]. It is derived by assuming uniform prior distributions on the values of an attribute for each possible instantiation of its parent attributes. This assumption introduces a tendency to select simpler network structures. In this paper we modify the K2 metric in three different ways, introducing a parameter by which the strength of this tendency can be controlled. Our experiments with the ALARM network [2] and the BOBLO network [17] suggest that—somewhat contrary to our expectations—a slightly stronger tendency towards simpler structures may lead to even better results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
S.K. Andersen, K.G. Olesen, F.V. Jensen, and F. Jensen. HUGIN —A Shell for Building Bayesian Belief Universes for Expert Systems. Proc. 11th Int. J. Conf. on Artificial Intelligence (IJCAI’89, Detroit, MI, USA), 1080–1085. Morgan Kaufmann, San Mateo, CA, SA 1989
I.A. Beinlich, H.J. Suermondt, R.M. Chavez, and D.F. Cooper. The ALARM Monitoring System: A Case Study with Two Probabilistic Inference Techniques for Belief Networks. Proc. Conf. on AI in Medical Care, London, United Kingdom 1989
C. Borgelt and R. Kruse. Evaluation Measures for Learning Probabilistic and Possibilistic Networks. Proc. 6th IEEE Int. Conf. on Fuzzy Systems (FUZZ-IEEE’97, Barcelona, Spain), Vol. 2:1034–1038. IEEE Press, Piscataway, NJ, USA 1997
L. Breiman, J.H. Friedman, R.A. Olshen, and C.J. Stone. Classification and Regression Trees, Wadsworth International Group, Belmont, CA, USA 1984
W. Buntine. Theory Refinement on Bayesian Networks. Proc. 7th Conf. on Uncertainty in Artificial Intelligence (UAI’91, Los Angeles, CA, USA), 52–60. Morgan Kaufmann, San Mateo, CA, USA 1991
C.K. Chow and C.N. Liu. Approximating Discrete Probability Distributions with Dependence Trees. IEEE Trans. on Information Theory 14(3):462–467, IEEE Press, Piscataway, NJ, USA 1968
G.F. Cooper and E. Herskovits. A Bayesian Method for the Induction of Probabilistic Networks from Data. Machine Learning 9:309–347. Kluwer, Amsterdam, Netherlands 1992
P.G.L. Dirichlet. Sur un nouvelle methode pour la determination des integrales multiples. Comp. Rend. Acad. Science 8:156–160. France 1839
D. Heckerman. Probabilistic Similarity Networks. MIT Press, Cambridge, MA, USA 1991
D. Heckerman, D. Geiger, and D.M. Chickering. Learning Bayesian Networks: The Combination of Knowledge and Statistical Data. Machine Learning 20:197–243. Kluwer, Amsterdam, Netherlands 1995
I. Kononenko. On Biases in Estimating Multi-Valued Attributes. Proc. 1st Int. Conf. on Knowledge Discovery and Data Mining (KDD’95, Montreal, Canada), 1034–1040. AAAI Press, Menlo Park, CA, USA 1995
R. Kruse, E. Schwecke, and J. Heinsohn. Uncertainty and Vagueness in Knowledge-based Systems: Numerical Methods. Springer, Berlin, Germany 1991
S. Kullback and R.A. Leibler. On Information and Sufficiency. Ann. Math. Statistics 22:79–86. Institute of Mathematical Statistics, Hayward, CA, USA 1951
S.L. Lauritzen and D.J. Spiegelhalter. Local Computations with Probabilities on Graphical Structures and Their Application to Expert Systems. J. Royal Statistical Society, Series B, 2(50):157–224. Blackwell, Oxford, United Kingdom 1988
J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference 2nd edition Morgan Kaufman, San Mateo, CA, USA 1992
J.R. Quinlan. C4.5: Programs for Machine Learning, Morgan Kaufman, San Mateo, CA, USA 1993
L.K. Rasmussen. Blood Group Determination of Danish Jersey Cattle in the F-blood Group System. Dina Foulum, Tjele, Denmark 1992
J. Rissanen. Stochastic Complexity. Journal of the Royal Statistical Society (Series B), 49:223–239. Blackwell, Oxford, United Kingdom 1987
L. Wehenkel. On Uncertainty Measures Used for Decision Tree Induction. Proc. 7th Int. Conf. on Inf. Proc. and Management of Uncertainty in Knowledge-based Systems (IPMU’96, Granada, Spain), 413–417. Universidad de Granada, Spain1996
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Borgelt, C., Kruse, R. (2001). An Empirical Investigation of the K2 Metric. In: Benferhat, S., Besnard, P. (eds) Symbolic and Quantitative Approaches to Reasoning with Uncertainty. ECSQARU 2001. Lecture Notes in Computer Science(), vol 2143. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44652-4_22
Download citation
DOI: https://doi.org/10.1007/3-540-44652-4_22
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42464-2
Online ISBN: 978-3-540-44652-1
eBook Packages: Springer Book Archive