# Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

Source: [Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties](<https://www.sota2.com/research/paper/68fa69901e209131cea22aa4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:02:46.333Z

Authors: Lisa Schut, Oscar Key, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal

Published: 2021-03-16T10:20:24.000Z

## Abstract

Counterfactual explanations (CEs) are a practical tool for demonstrating why machine learning classifiers make particular decisions. For CEs to be useful, it is important that they are easy for users to interpret. Existing methods for generating interpretable CEs rely on auxiliary generative models, which may not be suitable for complex datasets, and incur engineering overhead. We introduce a simple and fast method for generating interpretable CEs in a white-box setting without an auxiliary model, by using the predictive uncertainty of the classifier. Our experiments show that our proposed algorithm generates more interpretable CEs, according to IM1 scores, than existing methods. Additionally, our approach allows us to estimate the uncertainty of a CE, which may be important in safety-critical applications, such as those in the medical domain.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Counterfactual Explanations on PneumoniaMNIST (test)](<https://www.sota2.com/research/sota/counterfactual-explanations-on-pneumoniamnist-test.md>): Counterfactual Explanations; PneumoniaMNIST (test); IM1: 1.157.

- [Counterfactual Explanations on Spam (test)](<https://www.sota2.com/research/sota/counterfactual-explanations-on-spam-test.md>): Counterfactual Explanations; Spam (test); IM1: 1.2756.

- [Counterfactual Explanation on MNIST (test)](<https://www.sota2.com/research/sota/counterfactual-explanation-on-mnist-test.md>): Counterfactual Explanation; MNIST (test); Validity Score: 96.

- [Counterfactual Explanations on MNIST (test)](<https://www.sota2.com/research/sota/counterfactual-explanations-on-mnist-test.md>): Counterfactual Explanations; MNIST (test); IM1 Score: 1.2373.

- [Counterfactual Explanations on Credit (test)](<https://www.sota2.com/research/sota/counterfactual-explanations-on-credit-test.md>): Counterfactual Explanations; Credit (test); IM1: 0.9251.

- [Counterfactual Explanations on Breast Cancer (test)](<https://www.sota2.com/research/sota/counterfactual-explanations-on-breast-cancer-test.md>): Counterfactual Explanations; Breast Cancer (test); IM1: 1.1151.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.08951>)

[PDF](<https://arxiv.org/pdf/2103.08951.pdf>)