Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions

07/20/2021
by   Eoin Delaney, et al.
0

Whilst an abundance of techniques have recently been proposed to generate counterfactual explanations for the predictions of opaque black-box systems, markedly less attention has been paid to exploring the uncertainty of these generated explanations. This becomes a critical issue in high-stakes scenarios, where uncertain and misleading explanations could have dire consequences (e.g., medical diagnosis and treatment planning). Moreover, it is often difficult to determine if the generated explanations are well grounded in the training data and sensitive to distributional shifts. This paper proposes several practical solutions that can be leveraged to solve these problems by establishing novel connections with other research works in explainability (e.g., trust scores) and uncertainty estimation (e.g., Monte Carlo Dropout). Two experiments demonstrate the utility of our proposed solutions.

READ FULL TEXT

page 4

page 7

page 9

research
12/16/2022

Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ

Counterfactual explanations have emerged as a popular solution for the e...
research
07/15/2022

CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN

Deep learning models used in medical image analysis are prone to raising...
research
03/24/2022

Effective Explanations for Entity Resolution Models

Entity resolution (ER) aims at matching records that refer to the same r...
research
10/23/2020

Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification

Corporate mergers and acquisitions (M A) account for billions of dolla...
research
08/11/2020

How Much Should I Trust You? Modeling Uncertainty of Black Box Explanations

As local explanations of black box models are increasingly being employe...
research
10/21/2022

Augmentation by Counterfactual Explanation – Fixing an Overconfident Classifier

A highly accurate but overconfident model is ill-suited for deployment i...
research
01/02/2019

Efficient Search for Diverse Coherent Explanations

This paper proposes new search algorithms for counterfactual explanation...

Please sign up or login with your details

Forgot password? Click here to reset