Evaluating the difference between graph structures in Gaussian Bayesian networks

Authors:
Miguel Ángel Gómez-Villegas;Paloma Main;Hilario Navarro;Rosario Susi
Affiliations:
Dpto. Estadística e I.O., Fac. Ciencias Matemáticas, Univ. Complutense de Madrid, 28040 Madrid, Spain;Dpto. Estadística e I.O., Fac. Ciencias Matemáticas, Univ. Complutense de Madrid, 28040 Madrid, Spain;Dpto. de Estadística, I.O. y Cálc. Numérico, Fac. Ciencias, UNED, 28040 Madrid, Spain;Dpto. Estadística e I.O. III, E.U. Estadística, Univ. Complutense de Madrid, 28040 Madrid, Spain
Venue:
Expert Systems with Applications: An International Journal
Year:
2011

Citing 6
Cited 1

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
Gaussian influence diagrams

Management Science
Making Sensitivity Analysis Computationally Efficient

UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
Sensitivity analysis: an aid for belief-network quantification

The Knowledge Engineering Review
Bayesian Networks and Decision Graphs

Bayesian Networks and Decision Graphs
A distance measure for bounding probabilistic belief change

International Journal of Approximate Reasoning

The effect of block parameter perturbations in Gaussian Bayesian networks: Sensitivity and robustness

Information Sciences: an International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

In this work, we evaluate the sensitivity of Gaussian Bayesian networks to perturbations or uncertainties in the regression coefficients of the network arcs and the conditional distributions of the variables. The Kullback-Leibler divergence measure is used to compare the original network to its perturbation. By setting the regression coefficients to zero or non-zero values, the proposed method can remove or add arcs, making it possible to compare different network structures. The methodology is implemented with some case studies.