On Fairness and Interpretability

Deepak Padmanabhan, Sanil V, Joemon Jose

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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
Original languageEnglish
Title of host publicationIJCAI 2020 AI for Social Good workshop: Proceedings
Number of pages4
Publication statusAccepted - 08 Nov 2020
EventIJCAI 2020 AI for Social Good workshop -
Duration: 08 Jan 202108 Jan 2021
https://crcs.seas.harvard.edu/event/ai-social-good-workshop-0

Publication series

Name
ISSN (Print)1111-1111

Conference

ConferenceIJCAI 2020 AI for Social Good workshop
Period08/01/202108/01/2021
Internet address

Cite this