Bayesian Network Structural Learning and Incomplete Data
Philippe Leray and Olivier François
In: AKRR'05 International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning, 15-17 June 2005, Helsinki, Finland.
Bayesien networks formalisme is becomming increasingly popular in a lot of areas such as decision aid, diagnosis and complex systems control, in particular thanks to its inference capabilities, even when data are incomplete.
Besides, estimating the parameters of a fixed-structure Bayesian network is easy. However, very few methods are capable of using incomplete cases as a base to determine the structure of a Bayesian network.
In this paper, we take up the structural EM algorithm principle and put forward some potential improvements based upon principles recetly developed in structural learning with complete data.