Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 73 of its 148 references that are in the map. First posted on arXiv 29 Apr 2024.
Builds on
73 of 148 references.
References · 73
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
- 2018Datasheets for Datasetscited by 1,386
- 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
- 2018Model Cards for Model Reportingcited by 1,080
- 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
- 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
- 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 384
- 2018Delayed Impact of Fair Machine Learningcited by 184
38 more
- 2018Path-Specific Counterfactual Fairnesscited by 181
- 2019REPAIR: Removing Representation Bias by Dataset Resamplingcited by 157
- 2017Fairness in Machine Learning: Lessons from Political Philosophycited by 149
- 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
- 2020Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertaintycited by 129
- 2022Machine Learning Operations (MLOps): Overview, Definition, and Architecturecited by 128
- 2019On the Apparent Conflict Between Individual and Group Fairnesscited by 126
- 2019Towards a Critical Race Methodology in Algorithmic Fairnesscited by 125
- 2021What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Researchcited by 119
- 2021Counterfactual Explanations Can Be Manipulatedcited by 113
- 2019"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanationscited by 111
- 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
- 2018'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisionscited by 91
- 2023Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanationscited by 83
- 2019Fairwashing: the risk of rationalizationcited by 81
- 2020Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AIcited by 81
- 2023Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision supportcited by 66
- 2022Fairness Testing: A Comprehensive Survey and Analysis of Trendscited by 62
- 2019FairSight: Visual Analytics for Fairness in Decision Makingcited by 59
- 2017A Voting-Based System for Ethical Decision Makingcited by 55
- 2019Equalizing Recourse across Groupscited by 55
- 2020The Pragmatic Turn in Explainable Artificial Intelligence (XAI)cited by 54
- 2017The Promise and Peril of Human Evaluation for Model Interpretabilitycited by 52
- 2019FlipTest: Fairness Testing via Optimal Transportcited by 51
- 2018Explanation Methods in Deep Learning: Users, Values, Concerns and Challengescited by 49
- 2019How model accuracy and explanation fidelity influence user trustcited by 45
- 2022Performative Powercited by 43
- 2020What's Sex Got To Do With Fair Machine Learning?cited by 38
- 2017Society-in-the-Loop: Programming the Algorithmic Social Contractcited by 35
- 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
- 2021Fairness Perceptions of Algorithmic Decision-Making: A Systematic Review of the Empirical Literaturecited by 27
- 2022Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Makingcited by 25
- 2019This Thing Called Fairness: Disciplinary Confusion Realizing a Value in Technologycited by 24
- 2020Making Fair ML Software using Trustworthy Explanationcited by 24
- 2019Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Datacited by 23
- 2020FairLens: Auditing Black-box Clinical Decision Support Systemscited by 23
- 2022Marrying Fairness and Explainability in Supervised Learningcited by 23
- 2017Machine Learning for Networking: Workflow, Advances and Opportunitiescited by 20
50 most cited of 73 All 73 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.