Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Luca Deck, Astrid Schomäcker, Timo Speith, Jakob Schöffer, Lena Kästner, Niklas Kühl

TL;DR

This paper distill eight fairness desiderata, map them along the AI lifecycle, and discusses how XAI could help address each of them, to provide orientation for practical applications and to inspire XAI research specifically focused on these fairness desiderata.

Abstract

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.

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

TL;DR

This paper distill eight fairness desiderata, map them along the AI lifecycle, and discusses how XAI could help address each of them, to provide orientation for practical applications and to inspire XAI research specifically focused on these fairness desiderata.

Abstract

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.
Paper Structure (16 sections, 2 figures, 1 table)

This paper contains 16 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background
  3. Algorithmic Fairness
  4. Considerations of Fairness Along the AI Lifecycle Remain Incomplete
  5. Considerations of XAI for Fairness Remain Incomplete
  6. How XAI Can Be Leveraged for Fairness Along the AI Lifecycle
  7. Fairness Understanding
  8. Data Fairness
  9. Formal Fairness
  10. Perceived Fairness
  11. Fairness With Human Oversight
  12. Empowering Fairness
  13. Long-Term Fairness
  14. Informational Fairness
  15. The COMPAS Case
  16. ...and 1 more sections

Figures (2)

  • Figure 1: The AI Lifecycle we use, combined from quemy2020twoquemy2020two and wang2017machinewang2017machine.
  • Figure 2: Fairness desiderata along the AI lifecycle depicting how XAI may directly contribute to these desiderata and how it may contribute to informational fairness across all desiderata (symbolized by speakerphones).