
A unified framework that can effectively integrate diverse types of probabilistic domain knowledge into the parameter learning of Probabilistic Circuits, enabling improved generalization and robustness in data-scarce and noisy settings.


coremsg

integrating-domain-knowledge-into-learning-probabilistic-circuits-for-improved-generalization-and-robustness


Integrating Domain Knowledge into Learning Probabilistic Circuits for Improved Generalization and Robustness
