Fairness May Backfire: When Leveling-Down Occurs in Fair Machine Learning

• URL: http://arxiv.org/abs/2603.06901v1
• Date: Fri, 06 Mar 2026 21:38:46 GMT
• Title: Fairness May Backfire: When Leveling-Down Occurs in Fair Machine Learning
• Abstract summary: We show that in the attribute-aware regime, fair ML necessarily (weakly) improves outcomes for the disadvantaged group.<n>In the attribute-blind regime, fairness can shift both groups' outcomes in the same direction, leading to either leveling up or leveling down.<n>Our results provide structural guidance on when pursuing algorithmic fairness is likely to improve group outcomes.
• Score: 17.3262089857067
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As machine learning (ML) systems increasingly shape access to credit, jobs, and other opportunities, the fairness of algorithmic decisions has become a central concern. Yet it remains unclear when enforcing fairness constraints in these systems genuinely improves outcomes for affected groups or instead leads to "leveling down," making one or both groups worse off. We address this question in a unified, population-level (Bayes) framework for binary classification under prevalent group fairness notions. Our Bayes approach is distribution-free and algorithm-agnostic, isolating the intrinsic effect of fairness requirements from finite-sample noise and from training and intervention specifics. We analyze two deployment regimes for ML classifiers under common legal and governance constraints: attribute-aware decision-making (sensitive attributes available at decision time) and attribute-blind decision-making (sensitive attributes excluded from prediction). We show that, in the attribute-aware regime, fair ML necessarily (weakly) improves outcomes for the disadvantaged group and (weakly) worsens outcomes for the advantaged group. In contrast, in the attribute-blind regime, the impact of fairness is distribution-dependent: fairness can benefit or harm either group and may shift both groups' outcomes in the same direction, leading to either leveling up or leveling down. We characterize the conditions under which these patterns arise and highlight the role of "masked" candidates in driving them. Overall, our results provide structural guidance on when pursuing algorithmic fairness is likely to improve group outcomes and when it risks systemic leveling down, informing fair ML design and deployment choices.

Related papers

• Fairness vs Performance: Characterizing the Pareto Frontier of Algorithmic Decision Systems [0.0]
  Design of fair algorithmic decision systems requires balancing model performance with fairness toward affected individuals.<n>We investigate fairness in binary prediction-based decision problems by conceptualizing decision making as a multi-objective optimization problem.
  arXiv  Detail & Related papers  (2026-05-11T14:04:27Z)
• Post-hoc Provider Fairness Adaptation via Hierarchical Exposure Alignment [54.58748721533078]
  Post-hoc Fairness Adaptation (PFA) is a lightweight framework that equips a frozen recommender with a fairness adapter.<n>It learns personalized additive score adjustments from user-item embeddings to steer provider exposure toward fairness.<n>PFA achieves substantial fairness gains with negligible accuracy loss, consistently outperforming strong baselines.
  arXiv  Detail & Related papers  (2026-05-02T16:32:52Z)
• Individual Fairness In Strategic Classification [7.903744240517792]
  Strategic classification, where individuals modify their features to influence machine learning (ML) decisions, presents critical fairness challenges.<n>We analyze threshold-based classifiers and prove that deterministic thresholds violate individual fairness.<n>We introduce conditions under which a randomized classifier ensures individual fairness and leverage these conditions to find an optimal and individually fair randomized classifier.<n> Experiments on real-world datasets confirm that our method effectively mitigates unfairness and improves the fairness-accuracy trade-off.
  arXiv  Detail & Related papers  (2026-02-04T22:09:18Z)
• Fairness under Competition [8.497866040398053]
  We consider the effects of adopting fair classifiers on the overall level of ecosystem fairness.<n>We show that even if competing classifiers are individually fair, the ecosystem's outcome may be unfair.
  arXiv  Detail & Related papers  (2025-05-22T06:43:15Z)
• Finite-Sample and Distribution-Free Fair Classification: Optimal Trade-off Between Excess Risk and Fairness, and the Cost of Group-Blindness [14.421493372559762]
  We quantify the impact of enforcing algorithmic fairness and group-blindness in binary classification under group fairness constraints. We propose a unified framework for fair classification that provides distribution-free and finite-sample fairness guarantees with controlled excess risk.
  arXiv  Detail & Related papers  (2024-10-21T20:04:17Z)
• Fairness-Accuracy Trade-Offs: A Causal Perspective [58.06306331390586]
  We analyze the tension between fairness and accuracy from a causal lens for the first time.<n>We show that enforcing a causal constraint often reduces the disparity between demographic groups.<n>We introduce a new neural approach for causally-constrained fair learning.
  arXiv  Detail & Related papers  (2024-05-24T11:19:52Z)
• A Unified Post-Processing Framework for Group Fairness in Classification [10.615965454674901]
  We present a post-processing algorithm for fair classification that covers group fairness criteria including statistical parity, equal opportunity, and equalized odds under a single framework.<n>Our algorithm, called "LinearPost", achieves fairness post-hoc by linearly transforming the predictions of the (unfair) base predictor with a "fairness risk" according to a weighted combination of the (predicted) group memberships.
  arXiv  Detail & Related papers  (2024-05-07T05:58:44Z)
• 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)
• 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)
• MultiFair: Multi-Group Fairness in Machine Learning [52.24956510371455]
  We study multi-group fairness in machine learning (MultiFair) We propose a generic end-to-end algorithmic framework to solve it. Our proposed framework is generalizable to many different settings.
  arXiv  Detail & Related papers  (2021-05-24T02:30:22Z)
• Beyond Individual and Group Fairness [90.4666341812857]
  We present a new data-driven model of fairness that is guided by the unfairness complaints received by the system. Our model supports multiple fairness criteria and takes into account their potential incompatibilities.
  arXiv  Detail & Related papers  (2020-08-21T14:14:44Z)

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.