Improving Bayesian Network Structure Learning in the Presence of Measurement Error
This work is significant for researchers and practitioners who apply Bayesian network structure learning to real-world datasets, as it mitigates the problem of measurement error leading to inaccurate network structures.
This paper addresses the issue of spurious edges in Bayesian network structure learning caused by measurement error in observational data. The authors propose a correction algorithm, implemented as an additional learning phase, that successfully removes false positive edges and improves the graphical score of four established structure learning algorithms.
Structure learning algorithms that learn the graph of a Bayesian network from observational data often do so by assuming the data correctly reflect the true distribution of the variables. However, this assumption does not hold in the presence of measurement error, which can lead to spurious edges. This is one of the reasons why the synthetic performance of these algorithms often overestimates real-world performance. This paper describes an algorithm that can be added as an additional learning phase at the end of any structure learning algorithm, and serves as a correction learning phase that removes potential false positive edges. The results show that the proposed correction algorithm successfully improves the graphical score of four well-established structure learning algorithms spanning different classes of learning in the presence of measurement error.