Deep interpretable ensembles

TL;DR

This paper introduces transformation ensembles that combine probabilistic deep models while maintaining interpretability and outperforming traditional deep ensembles in uncertainty quantification and prediction accuracy.

Contribution

It proposes a novel transformation ensemble method that preserves interpretability and improves prediction quality compared to standard deep ensembles.

Findings

Transformation ensembles perform comparably to classical deep ensembles in accuracy.

They effectively quantify both aleatoric and epistemic uncertainty.

They produce minimax optimal predictions under certain conditions.

Abstract

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.