Bayesian Network Structure Learning with Side Constraints


Andrew Li, Peter Beek ;
Proceedings of the Ninth International Conference on Probabilistic Graphical Models, PMLR 72:225-236, 2018.


Hybrid methods for Bayesian network structure learning that incorporate both observed data and expert knowledge have proven to be important in many fields. Previous studies have presented both exact and approximate hybrid methods for structure learning. In this paper, we propose an approximate method based on local search that is capable of efficiently handling a variety of prior knowledge constraints, including an important class of non-decomposable \emph{ancestral} constraints that assert indirect causation between random variables. In our experiments, our proposed approximate method is able to significantly outperform an existing state-of-the-art approximate method in finding feasible solutions when \emph{hard constraints} are imposed. Our approach is able to find near-optimal networks while scaling up to almost fifty random variables. In contrast, previous exact methods are unable to handle more than twenty random variables. Furthermore, we show that when prior knowledge is integrated, we are often able to produce a network much closer to the ground truth network, particularly when the amount of data is limited.

Related Material