Discovering Hidden Variables: A Structure-Based Approach
G. Elidan, N. Lotner, N. Friedman, and D. Koller.
To appear in NIPS, 2000.
Postscript version (178K)
A serious problem in learning probabilistic models is the presence of
hidden variables. These variables are not
observed, yet interact with several of the observed variables. As
such, they induce seemingly complex dependencies among the latter.
In recent years, much attention has been devoted to the
development of algorithms for learning parameters, and in some cases
structure, in the presence of hidden variables.
In this paper, we address the related problem of detecting
hidden variables that interact with the observed variables. This problem
is of interest both for improving our understanding of the domain and
as a preliminary step that guides the learning procedure towards
promising models. A very natural approach is to search for ``structural
signatures'' of hidden variables --- substructures in the learned network
that tend to suggest the presence of a hidden variable. We make this
idea concrete, and show how to integrate it with structure-search
algorithms. We evaluate this method on several synthetic and real-life
datasets, and show that it performs surprisingly well.
Back to Nir's publications page