Measuring Perceptions of Fairness in AI Systems: The Effects of Infra-marginality

• URL: http://arxiv.org/abs/2603.05889v1
• Date: Fri, 06 Mar 2026 04:15:52 GMT
• Title: Measuring Perceptions of Fairness in AI Systems: The Effects of Infra-marginality
• Abstract summary: We present a user study with 85 participants in a hypothetical medical decision-making scenario.<n>Our results show that participants did not equate fairness with simple statistical parity.<n>These findings highlight that fairness judgments are shaped not only by outcomes, but also by beliefs about the causes of disparities.
• Score: 2.48490797934472
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Differences in data distributions between demographic groups, known as the problem of infra-marginality, complicate how people evaluate fairness in machine learning models. We present a user study with 85 participants in a hypothetical medical decision-making scenario to examine two treatments: group-specific model performance and training data availability. Our results show that participants did not equate fairness with simple statistical parity. When group-specific performances were equal or unavailable, participants preferred models that produced equal outcomes; when performances differed, especially in ways consistent with data imbalances, they judged models that preserved those differences as more fair. These findings highlight that fairness judgments are shaped not only by outcomes, but also by beliefs about the causes of disparities. We discuss implications for popular group fairness definitions and system design, arguing that accounting for distributional context is critical to aligning algorithmic fairness metrics with human expectations in real-world applications.

Related papers

• On the use of graph models to achieve individual and group fairness [0.6299766708197883]
  We provide a theoretical framework based on Sheaf Diffusion to leverage tools based on dynamical systems and homology to model fairness.<n>We present a collection of network topologies handling different fairness metrics, leading to a unified method capable of dealing with both individual and group bias.<n>The paper showcases the performance of the proposed models in terms of accuracy and fairness.
  arXiv  Detail & Related papers  (2026-01-13T18:17:43Z)
• Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness [49.35494016290887]
  We show that equal performance across subgroups is an unreliable measure of fairness when data are representative of relevant populations but reflective of real-world disparities.<n>Our framework suggests complementing disaggregated evaluations with explicit causal assumptions and analysis to control for confounding and distribution shift.
  arXiv  Detail & Related papers  (2025-06-04T17:40:31Z)
• Fairness Perceptions in Regression-based Predictive Models [0.19999259391104385]
  This paper introduces three novel divergence-based group fairness notions to assess the fairness of regression-based analytics tools.<n>Crowd feedback is used to estimate social fairness preferences.<n>The findings clearly depict a strong preference towards the separation and sufficiency fairness notions, and that the predictive analytics is deemed fair with respect to gender and race groups, but unfair in terms of age groups.
  arXiv  Detail & Related papers  (2025-05-08T01:48:27Z)
• The Flawed Foundations of Fair Machine Learning [0.0]
  We show that there is a trade-off between statistically accurate outcomes and group similar outcomes in any data setting where group disparities exist. We introduce a proof-of-concept evaluation to aid researchers and designers in understanding the relationship between statistically accurate outcomes and group similar outcomes.
  arXiv  Detail & Related papers  (2023-06-02T10:07:12Z)
• Counterpart Fairness -- Addressing Systematic between-group Differences in Fairness Evaluation [17.495053606192375]
  When using machine learning to aid decision-making, it is critical to ensure that an algorithmic decision is fair and does not discriminate against specific individuals/groups. Existing group fairness methods aim to ensure equal outcomes across groups delineated by protected variables like race or gender. In cases where systematic differences between groups play a significant role in outcomes, these methods may overlook the influence of non-protected variables.
  arXiv  Detail & Related papers  (2023-05-29T15:41:12Z)
• DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision [73.80009454050858]
  This work presents a self-supervised model, called DualFair, that can debias sensitive attributes like gender and race from learned representations. Our model jointly optimize for two fairness criteria - group fairness and counterfactual fairness.
  arXiv  Detail & Related papers  (2023-03-15T07:13:54Z)
• FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification [14.589159162086926]
  We propose FairAdaBN, which makes batch normalization adaptive to sensitive attribute. We propose a new metric, named Fairness-Accuracy Trade-off Efficiency (FATE), to compute normalized fairness improvement over accuracy drop. Experiments on two dermatological datasets show that our proposed method outperforms other methods on fairness criteria and FATE.
  arXiv  Detail & Related papers  (2023-03-15T02:22:07Z)
• Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective [50.093280002375984]
  Performance unfairness among variables widely exists in multivariate time series (MTS) forecasting models. We propose a novel framework, named FairFor, for fairness-aware MTS forecasting.
  arXiv  Detail & Related papers  (2023-01-27T04:54:12Z)
• Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization? [90.35044668396591]
  A recurring theme in machine learning is algorithmic monoculture: the same systems, or systems that share components, are deployed by multiple decision-makers. We propose the component-sharing hypothesis: if decision-makers share components like training data or specific models, then they will produce more homogeneous outcomes. We test this hypothesis on algorithmic fairness benchmarks, demonstrating that sharing training data reliably exacerbates homogenization. We conclude with philosophical analyses of and societal challenges for outcome homogenization, with an eye towards implications for deployed machine learning systems.
  arXiv  Detail & Related papers  (2022-11-25T09:33:11Z)
• Measuring Fairness of Text Classifiers via Prediction Sensitivity [63.56554964580627]
  ACCUMULATED PREDICTION SENSITIVITY measures fairness in machine learning models based on the model's prediction sensitivity to perturbations in input features. We show that the metric can be theoretically linked with a specific notion of group fairness (statistical parity) and individual fairness.
  arXiv  Detail & Related papers  (2022-03-16T15:00:33Z)
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
  We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
  arXiv  Detail & Related papers  (2021-09-17T13:45:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.