A Human-in-the-loop Framework to Construct Context-aware Mathematical Notions of Outcome Fairness
This work addresses the need for more context-sensitive fairness definitions in machine learning, though it is an incremental step toward stakeholder involvement.
The paper tackles the problem that existing fairness notions ignore decision-making context by proposing a human-in-the-loop framework to learn context-aware mathematical fairness formulations, illustrated in a criminal risk assessment scenario with human experiments.
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.