Explaining predictive uncertainty by exposing second-order effects

Florian Bley, Sebastian Lapuschkin, Wojciech Samek, Grégoire Montavon

Abstract: Highlights•Explaining the predictive uncertainty of an ML model is practically relevant.•Second-order effects are found to be dominant in uncertainty estimates.•An efficient method for attributing uncertainty to input features is proposed.•Evaluations and showcases demonstrate the accuracy and usefulness of the method.