mlsanityData to 13 Oct 2026

The Cost of Local and Global Fairness in Federated Learning

arXiv 2503.22762 ↗First posted 27 Mar 2025cs.LG cs.AI cs.CYcited by 2

Not on the map. Why?

Abstract (arXiv)

With the emerging application of Federated Learning (FL) in finance, hiring and healthcare, FL models are regulated to be fair, preventing disparities with respect to legally protected attributes such as race or gender. Two concepts of fairness are important in FL: global and local fairness. Global fairness addresses the disparity across the entire population and local fairness is concerned with the disparity within each client. Prior fair FL frameworks have improved either global or local fairness without considering both. Furthermore, while the majority of studies on fair FL focuses on binary settings, many real-world applications are multi-class problems. This paper proposes a framework that investigates the minimum accuracy lost for enforcing a specified level of global and local fairness in multi-class FL settings. Our framework leads to a simple post-processing algorithm that derives fair outcome predictors from the Bayesian optimal score functions. Experimental results show that our algorithm outperforms the current state of the art (SOTA) with regard to the accuracy-fairness tradoffs, computational and communication costs. Codes are available at: https://github.com/papersubmission678/The-cost-of-local-and-global-fairness-in-FL .

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 24 of its 49 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

24 of 49 references.

References · 24

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
  2. 2019Advances and Open Problems in Federated Learningcited by 3,040
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,005
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,227
  5. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 444
  6. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  7. 2019Wasserstein Fair Classificationcited by 131
  8. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 117
  9. 2020Fairness-aware Agnostic Federated Learningcited by 87
  10. 2019Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classificationcited by 60
  11. 2020Mitigating Bias in Federated Learningcited by 56
  12. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
12 more
  1. 2022Fair and Optimal Classification via Post-Processingcited by 50
  2. 2021Improving Fairness via Federated Learningcited by 39
  3. 2022Fair learning with Wasserstein barycenters for non-decomposable performance measurescited by 24
  4. 2020Particle Swarm Optimized Federated Learning For Industrial IoT and Smart City Servicescited by 18
  5. 2022Attainability and Optimality: The Equalized Odds Fairness Revisitedcited by 10
  6. 2022FAIR-FATE: Fair Federated Learning with Momentumcited by 10
  7. 2023Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decompositioncited by 10
  8. 2024Intrinsic Fairness-Accuracy Tradeoffs under Equalized Oddscited by 7
  9. 2021Neyman-Pearson Multi-class Classification via Cost-sensitive Learningcited by 6
  10. 2024Achieving Fairness Across Local and Global Models in Federated Learningcited by 5
  11. 2024Post-Fair Federated Learning: Achieving Group and Community Fairness in Federated Learning via Post-processingcited by 4
  12. 2024Minimax Optimal Fair Classification with Bounded Demographic Disparitycited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learningcited by 0
  2. 2026Patient-Conditioned Adaptive Offsets for Reliable Diagnosis across Subgroupscited by 0