LIBRE: Learning Interpretable Boolean Rule Ensembles

[edit]

Graziano Mita, Paolo Papotti, Maurizio Filippone, Pietro Michiardi ;
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:245-255, 2020.

Abstract

We present a novel method—LIBRE—learn an interpretable classifier, which materializes as a set of Boolean rules. LIBRE uses an ensemble of bottom-up, weak learners operating on a random subset of features, which allows for the learning of rules that generalize well on unseen data even in imbalanced settings. Weak learners are combined with a simple union so that the final ensemble is also interpretable. Experimental results indicate that LIBRE efficiently strikes the right balance between prediction accuracy, which is competitive with black-box methods, and interpretability, which is often superior to alternative methods from the literature.

Related Material