On Fairness and Interpretability

TL;DR

This paper explores the relationship between fairness and interpretability in AI, proposing two principles-based frameworks to integrate these aspects for developing more ethical AI systems.

Contribution

It introduces two novel frameworks that combine fairness and interpretability, fostering new directions in ethical AI research.

Findings

Developed interpretability for fairness framework

Proposed fairness and interpretability integration framework

Aims to guide future ethical AI development

Abstract

Ethical AI spans a gamut of considerations. Among these, the most popular ones, fairness and interpretability, have remained largely distinct in technical pursuits. We discuss and elucidate the differences between fairness and interpretability across a variety of dimensions. Further, we develop two principles-based frameworks towards developing ethical AI for the future that embrace aspects of both fairness and interpretability. First, interpretability for fairness proposes instantiating interpretability within the realm of fairness to develop a new breed of ethical AI. Second, fairness and interpretability initiates deliberations on bringing the best aspects of both together. We hope that these two frameworks will contribute to intensifying scholarly discussions on new frontiers of ethical AI that brings together fairness and interpretability.