Semi-parametric Expert Bayesian Network Learning with Gaussian Processes and Horseshoe Priors
This work addresses the challenge of enhancing interpretability and handling identifiability issues in Bayesian networks for real-world applications, representing an incremental improvement in semi-parametric modeling.
The paper tackles the problem of learning semi-parametric relationships in expert Bayesian networks by proposing a model that uses Gaussian processes and horseshoe priors to introduce minimal nonlinear components, and it demonstrates improved performance over state-of-the-art methods on synthetic and UCI Liver Disorders datasets with metrics like structural Hamming distance and test likelihood.
This paper proposes a model learning Semi-parametric relationships in an Expert Bayesian Network (SEBN) with linear parameter and structure constraints. We use Gaussian Processes and a Horseshoe prior to introduce minimal nonlinear components. To prioritize modifying the expert graph over adding new edges, we optimize differential Horseshoe scales. In real-world datasets with unknown truth, we generate diverse graphs to accommodate user input, addressing identifiability issues and enhancing interpretability. Evaluation on synthetic and UCI Liver Disorders datasets, using metrics like structural Hamming Distance and test likelihood, demonstrates our models outperform state-of-the-art semi-parametric Bayesian Network model.