Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deck, Luca, Schomäcker, Astrid, Speith, Timo, Schöffer, Jakob, Kästner, Lena, Kühl, Niklas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917706834378752
author Deck, Luca
Schomäcker, Astrid
Speith, Timo
Schöffer, Jakob
Kästner, Lena
Kühl, Niklas
author_facet Deck, Luca
Schomäcker, Astrid
Speith, Timo
Schöffer, Jakob
Kästner, Lena
Kühl, Niklas
contents The widespread use of artificial intelligence (AI) systems across various domains is increasingly surfacing issues related to algorithmic fairness, especially in high-stakes scenarios. Thus, critical considerations of how fairness in AI systems might be improved -- and what measures are available to aid this process -- are overdue. Many researchers and policymakers see explainable AI (XAI) as a promising way to increase fairness in AI systems. However, there is a wide variety of XAI methods and fairness conceptions expressing different desiderata, and the precise connections between XAI and fairness remain largely nebulous. Besides, different measures to increase algorithmic fairness might be applicable at different points throughout an AI system's lifecycle. Yet, there currently is no coherent mapping of fairness desiderata along the AI lifecycle. In this paper, we we distill eight fairness desiderata, map them along the AI lifecycle, and discuss how XAI could help address each of them. We hope to provide orientation for practical applications and to inspire XAI research specifically focused on these fairness desiderata.
format Preprint
id arxiv_https___arxiv_org_abs_2404_18736
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle
Deck, Luca
Schomäcker, Astrid
Speith, Timo
Schöffer, Jakob
Kästner, Lena
Kühl, Niklas
Machine Learning
Artificial Intelligence
Computers and Society
The widespread use of artificial intelligence (AI) systems across various domains is increasingly surfacing issues related to algorithmic fairness, especially in high-stakes scenarios. Thus, critical considerations of how fairness in AI systems might be improved -- and what measures are available to aid this process -- are overdue. Many researchers and policymakers see explainable AI (XAI) as a promising way to increase fairness in AI systems. However, there is a wide variety of XAI methods and fairness conceptions expressing different desiderata, and the precise connections between XAI and fairness remain largely nebulous. Besides, different measures to increase algorithmic fairness might be applicable at different points throughout an AI system's lifecycle. Yet, there currently is no coherent mapping of fairness desiderata along the AI lifecycle. In this paper, we we distill eight fairness desiderata, map them along the AI lifecycle, and discuss how XAI could help address each of them. We hope to provide orientation for practical applications and to inspire XAI research specifically focused on these fairness desiderata.
title Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle
topic Machine Learning
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2404.18736