[1911.03020] A Human-in-the-loop Framework to Construct Context-aware Mathematical Notions of Outcome Fairness

Existing mathematical notions of fairness fail to account for the context of decision-making. We argue that moral consideration of contextual factors is an inherently human task. So we present a framework to learn context-aware mathematical formulations of fairness by eliciting people's situated fairness assessments. Our family of fairness notions corresponds to a new interpretation of economic models of Equality of Opportunity (EOP), and it includes most existing notions of fairness as special cases. Our human-in-the-loop approach is designed to learn the appropriate parameters of the EOP family by utilizing human responses to pair-wise questions about decision subjects' circumstance and deservingness, and the harm/benefit imposed on them. We illustrate our framework in a hypothetical criminal risk assessment scenario by conducting a series of human-subject experiments on Amazon Mechanical Turk. Our work takes an important initial step toward empowering stakeholders to have a voice in the formulation of fairness for Machine Learning.

In the 4th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES-2021) A Human-in-the-loop Framework to Construct Context-aware Mathematical Notions of Outcome Fairness Mohammad Yaghini Andreas Krause Hoda Heidari University of Toronto…

related reading

• [arxiv] an algorithmic framework for fairness elicitationarxiv.org
• Frontiers | On Consequentialism and Fairnessfrontiersin.org
• Relative notions of fairnessfairmlbook.org
• Statistical Fairness - Turing Commonsalan-turing-institute.github.io
• Moral Machinemoralmachine.net
• When is automated decision making legitimate?fairmlbook.org
• Microsoft Word - 03_Trites Volume 11 issue 2 Final.docxgmj-canadianedition.ca
• [1907.10323] Fairness in Reinforcement Learningarxiv.org
• AI and prediction of criminal justice risk: revisiting the COMPAS dataset, experiments, and the problem of algorithmic bias and fairnesslink.springer.com
• Papers · Nikhil Garggargnikhil.com
• The impact of AI errors in a human-in-the-loop processlink.springer.com
• Different Kinds of Fairnessrbaumeisterexistentialcontrarian.substack.com