Two Simple Ways to Learn Individual Fairness Metrics from Data
Individual fairness is an intuitive definition of algorithmic fairness that addresses some of the drawbacks of group fairness. Despite its benefits, it depends on a task specific fair metric that encodes our intuition of what is fair and unfair for the ML task at hand, and the lack of a widely accepted fair metric for many ML tasks is the main barrier to broader adoption of individual fairness. In this paper, we present two simple ways to learn fair metrics from a variety of data types. We show empirically that fair training with the learned metrics leads to improved fairness on three machine learning tasks susceptible to gender and racial biases. We also provide theoretical guarantees on the statistical performance of both approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessVocal Bursts Valence PredictionSimilar Papers 제목 키워드 기반
Two Simple Ways to Learn Individual Fairness Metric from Data
Individual fairness was proposed to address some of the shortcomings of group fairness. Despite its benefits, it requires a task specific fairness metric that encodes our intuition of what is fair and what is unfair for …
BIG-bench Machine LearningFairnessVocal Bursts Valence PredictionExploring the impact of fairness-aware criteria in AutoML
Machine Learning (ML) systems are increasingly used to support decision-making processes that affect individuals. However, these systems often rely on biased data, which can lead to unfair outcomes against specific group…
Opportunistic Multi-aspect Fairness through Personalized Re-ranking
As recommender systems have become more widespread and moved into areas with greater social impact, such as employment and housing, researchers have begun to seek ways to ensure fairness in the results that such systems …
AttributeFairnessRecommendation SystemsRe-RankingCascaded Debiasing: Studying the Cumulative Effect of Multiple Fairness-Enhancing Interventions
Understanding the cumulative effect of multiple fairness enhancing interventions at different stages of the machine learning (ML) pipeline is a critical and underexplored facet of the fairness literature. Such knowledge …
FairnessIndividual Fairness in Hierarchical Clustering
Hierarchical clustering produces ultrametric representations that impose strong global geometric constraints and may distort local similarities in ways that disproportionately affect individual data points. We study hier…