Deep interpretable ensembles
This addresses the need for interpretable models in high-stake decision fields, offering an incremental improvement over existing deep ensemble methods.
The paper tackles the loss of interpretability in deep ensembles by proposing transformation ensembles that preserve interpretability while ensuring uniformly better predictions than individual members on average. Experiments on public datasets show they perform on par with classical deep ensembles in prediction performance, discrimination, and calibration.
Ensembles improve prediction performance and allow uncertainty quantification by aggregating predictions from multiple models. In deep ensembling, the individual models are usually black box neural networks, or recently, partially interpretable semi-structured deep transformation models. However, interpretability of the ensemble members is generally lost upon aggregation. This is a crucial drawback of deep ensembles in high-stake decision fields, in which interpretable models are desired. We propose a novel transformation ensemble which aggregates probabilistic predictions with the guarantee to preserve interpretability and yield uniformly better predictions than the ensemble members on average. Transformation ensembles are tailored towards interpretable deep transformation models but are applicable to a wider range of probabilistic neural networks. In experiments on several publicly available data sets, we demonstrate that transformation ensembles perform on par with classical deep ensembles in terms of prediction performance, discrimination, and calibration. In addition, we demonstrate how transformation ensembles quantify both aleatoric and epistemic uncertainty, and produce minimax optimal predictions under certain conditions.