What will it take to generate fairness-preserving explanations?

TL;DR

This paper investigates whether explanations of black-box models on tabular data preserve fairness properties, highlighting potential issues and proposing future research directions for fairness-aware explanations.

Contribution

It reveals that current explanation methods may not maintain the fairness of black-box models and suggests directions for developing fairness-preserving explanations.

Findings

Explanations can obscure or ignore fairness properties.

Current explanation algorithms may produce misleading fairness information.

Future research should focus on fairness-aware explanation methods.

Abstract

In situations where explanations of black-box models may be useful, the fairness of the black-box is also often a relevant concern. However, the link between the fairness of the black-box model and the behavior of explanations for the black-box is unclear. We focus on explanations applied to tabular datasets, suggesting that explanations do not necessarily preserve the fairness properties of the black-box algorithm. In other words, explanation algorithms can ignore or obscure critical relevant properties, creating incorrect or misleading explanations. More broadly, we propose future research directions for evaluating and generating explanations such that they are informative and relevant from a fairness perspective.