[arxiv] an algorithmic framework for fairness elicitation

Abstract:We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders. We introduce a framework in which pairs of individuals can be identified as requiring (approximately) equal treatment under a learned model, or requiring ordered treatment such as "applicant Alice should be at least as likely to receive a loan as applicant Bob". We provide a provably convergent and oracle efficient algorithm for learning the most accurate model subject to the elicited fairness constraints, and prove generalization bounds for both accuracy and fairness. This algorithm can also combine the elicited constraints with traditional statistical fairness notions, thus "correcting" or modifying the latter by the former. We report preliminary findings of a behavioral study of our framework using human-subject fairness constraints elicited on the COMPAS criminal recidivism dataset.

An Algorithmic Framework for Fairness Elicitation Christopher Jung*, Michael Kearns*, Seth Neel*, Aaron Roth*, Logan Stapleton†, Zhiwei Steven Wu‡ October 15, 2020 arXiv:1905.10660v2 [cs.LG] 14 Oct 2020 Abstract We consider…

saved by

• Rhea Acharya

related reading

• [1911.03020] A Human-in-the-loop Framework to Construct Context-aware Mathematical Notions of Outcome Fairnessarxiv.org
• Constitutional AI: Harmlessness from AI Feedbackarxiv.org
• AI and prediction of criminal justice risk: revisiting the COMPAS dataset, experiments, and the problem of algorithmic bias and fairnesslink.springer.com
• Statistical Fairness - Turing Commonsalan-turing-institute.github.io
• [1907.10323] Fairness in Reinforcement Learningarxiv.org
• [2503.10990] Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibriumarxiv.org
• Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimesarxiv.org
• Relative notions of fairnessfairmlbook.org
• Frontiers | On Consequentialism and Fairnessfrontiersin.org
• Performative Predictionarxiv.org
• Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternativesarxiv.org
• 0cfc9404f89400c5ed897035e0d3748c-Paper-Conference.pdfproceedings.neurips.cc