Operationalizing Individual Fairness with Pairwise Fair Representations
We revisit the notion of individual fairness proposed by Dwork et al. A central challenge in operationalizing their approach is the difficulty in eliciting a human specification of a similarity metric. In this paper, we propose an operationalization of individual fairness that does not rely on a human specification of a distance metric. Instead, we propose novel approaches to elicit and leverage side-information on equally deserving individuals to counter subordination between social groups. We model this knowledge as a fairness graph, and learn a unified Pairwise Fair Representation (PFR) of the data that captures both data-driven similarity between individuals and the pairwise side-information in fairness graph. We elicit fairness judgments from a variety of sources, including human judgments for two real-world datasets on recidivism prediction (COMPAS) and violent neighborhood prediction (Crime & Communities). Our experiments show that the PFR model for operationalizing individual fairness is practically viable.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessSimilar Papers 제목 키워드 기반
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
Individual fairness, the notion that "similar individuals should be treated similarly," provides a strong and flexible fairness guarantee for algorithmic decision makers. However, a barrier to implementing individual fai…
Disentangling and Operationalizing AI Fairness at LinkedIn
Operationalizing AI fairness at LinkedIn's scale is challenging not only because there are multiple mutually incompatible definitions of fairness but also because determining what is fair depends on the specifics and con…
FairnessWhat is Fair? Defining Fairness in Machine Learning for Health
Ensuring that machine learning (ML) models are safe, effective, and equitable across all patients is critical for clinical decision-making and for preventing the amplification of existing health disparities. In this work…
Decision MakingFairnessMortality PredictionToward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
While algorithmic fairness is a thriving area of research, in practice, mitigating issues of bias often gets reduced to enforcing an arbitrarily chosen fairness metric, either by enforcing fairness constraints during the…
FairnessOperationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies
Text-to-Image (T2I) generation models have been widely adopted across various industries, yet are criticized for frequently exhibiting societal stereotypes. While a growing body of research has emerged to evaluate and mi…
Prompt Engineering