Being Bayesian about Network Structure
Nir Friedman, Daphne Koller
Abstract:
In many domains, we are interested in analyzing the structure of the underlying distribution, e.g., whether one variable is a direct parent of the other. Bayesian modelselection attempts to find the MAP model and use its structure to answer these questions. However, when the amount of available data is modest, there might be many models that have nonnegligible posterior. Thus, we want compute the Bayesian posterior of a feature, i.e., the total posterior probability of all models that contain it. In this paper, we propose a new approach for this task. We first show how to efficiently compute a sum over the exponential number of networks that are consistent with a fixed ordering over network variables. This allows us to compute, for a given ordering, both the marginal probability of the data and the posterior of a feature. We then use this result as the basis for an algorithm that approximates the Bayesian posterior of a feature. Our approach uses a Markov Chain Monte Carlo (MCMC) method, but over orderings rather than over network structures. The space of orderings is much smaller and more regular than the space of structures, and has a smoother posterior `landscape'. We present empirical results on synthetic and reallife datasets that compare our approach to full model averaging (when possible), to MCMC over network structures, and to a nonBayesian bootstrap approach.
Keywords: Structure Learning, MCMC, Bayesian Model Averaging
Pages: 201210
PS Link: http://robotics.stanford.edu/~koller/papers/uai00fk.ps
PDF Link: /papers/00/p201friedman.pdf
BibTex:
@INPROCEEDINGS{Friedman00,
AUTHOR = "Nir Friedman
and Daphne Koller",
TITLE = "Being Bayesian about Network Structure",
BOOKTITLE = "Proceedings of the Sixteenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI00)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "2000",
PAGES = "201210"
}

