Measuring and signing fairness as performance under multiple stakeholder distributions
As learning machines increase their influence on decisions concerning human lives, analyzing their fairness properties becomes a subject of central importance. Yet, our best tools for measuring the fairness of learning systems are rigid fairness metrics encapsulated as mathematical one-liners, offer limited power to the stakeholders involved in the prediction task, and are easy to manipulate when we exhort excessive pressure to optimize them. To advance these issues, we propose to shift focus from shaping fairness metrics to curating the distributions of examples under which these are computed. In particular, we posit that every claim about fairness should be immediately followed by the tagline "Fair under what examples, and collected by whom?". By highlighting connections to the literature in domain generalization, we propose to measure fairness as the ability of the system to generalize under multiple stress tests -- distributions of examples with social relevance. We encourage each stakeholder to curate one or multiple stress tests containing examples reflecting their (possibly conflicting) interests. The machine passes or fails each stress test by falling short of or exceeding a pre-defined metric value. The test results involve all stakeholders in a discussion about how to improve the learning system, and provide flexible assessments of fairness dependent on context and based on interpretable data. We provide full implementation guidelines for stress testing, illustrate both the benefits and shortcomings of this framework, and introduce a cryptographic scheme to enable a degree of prediction accountability from system providers.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain GeneralizationFairnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The FairCeptron: A Framework for Measuring Human Perceptions of Algorithmic Fairness
Measures of algorithmic fairness often do not account for human perceptions of fairness that can substantially vary between different sociodemographics and stakeholders. The FairCeptron framework is an approach for study…
Decision MakingFairnessCascaded 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 …
FairnessFACT: A Diagnostic for Group Fairness Trade-offs
Group fairness, a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes, has been shown to conflict with one another, often with a nece…
AttributeDiagnosticFairnessBounding and Approximating Intersectional Fairness through Marginal Fairness
Discrimination in machine learning often arises along multiple dimensions (a.k.a. protected attributes); it is then desirable to ensure \emph{intersectional fairness} -- i.e., that no subgroup is discriminated against. I…
DescriptiveFairnessPC-Fairness: A Unified Framework for Measuring Causality-based Fairness
A recent trend of fair machine learning is to define fairness as causality-based notions which concern the causal connection between protected attributes and decisions. However, one common challenge of all causality-base…
counterfactualFairness