Reliable Uncertain Evidence Modeling in Bayesian Networks by Credal Networks
This work addresses the challenge of handling uncertain evidence in Bayesian networks for probabilistic reasoning, but it appears incremental as it builds on existing credal network methods.
The paper tackles the problem of modeling uncertain evidence in Bayesian networks by proposing a set-valued quantification approach, reducing evidence propagation to standard updating in an augmented credal network, and provides an efficient exact procedure for a subclass of instances.
A reliable modeling of uncertain evidence in Bayesian networks based on a set-valued quantification is proposed. Both soft and virtual evidences are considered. We show that evidence propagation in this setup can be reduced to standard updating in an augmented credal network, equivalent to a set of consistent Bayesian networks. A characterization of the computational complexity for this task is derived together with an efficient exact procedure for a subclass of instances. In the case of multiple uncertain evidences over the same variable, the proposed procedure can provide a set-valued version of the geometric approach to opinion pooling.