# The Cost of Local and Global Fairness in Federated Learning

arXiv: https://arxiv.org/abs/2503.22762 · HTML: https://mlsanity.com/paper/2503.22762/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Inherent Tradeoffs in Learning Fair Representations](https://mlsanity.com/paper/1906.08386/) (2019)
- [Wasserstein Fair Classification](https://mlsanity.com/paper/1907.12059/) (2019)
- [FairFed: Enabling Group Fairness in Federated Learning](https://mlsanity.com/paper/2110.00857/) (2021)
- [Fairness-aware Agnostic Federated Learning](https://mlsanity.com/paper/2010.05057/) (2020)
- [Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification](https://mlsanity.com/paper/1906.05082/) (2019)
- [Mitigating Bias in Federated Learning](https://mlsanity.com/paper/2012.02447/) (2020)
- [Fair and Optimal Classification via Post-Processing](https://mlsanity.com/paper/2211.01528/) (2022)
- [Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning](https://mlsanity.com/paper/2108.08435/) (2021)
- [Improving Fairness via Federated Learning](https://mlsanity.com/paper/2110.15545/) (2021)
- [Fair learning with Wasserstein barycenters for non-decomposable performance measures](https://mlsanity.com/paper/2209.00427/) (2022)
- [Particle Swarm Optimized Federated Learning For Industrial IoT and Smart City Services](https://mlsanity.com/paper/2009.02560/) (2020)
- [Attainability and Optimality: The Equalized Odds Fairness Revisited](https://mlsanity.com/paper/2202.11853/) (2022)
- [FAIR-FATE: Fair Federated Learning with Momentum](https://mlsanity.com/paper/2209.13678/) (2022)
- [Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition](https://mlsanity.com/paper/2307.11333/) (2023)
- [Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds](https://mlsanity.com/paper/2405.07393/) (2024)
- [Neyman-Pearson Multi-class Classification via Cost-sensitive Learning](https://mlsanity.com/paper/2111.04597/) (2021)
- [Achieving Fairness Across Local and Global Models in Federated Learning](https://mlsanity.com/paper/2406.17102/) (2024)
- [Post-Fair Federated Learning: Achieving Group and Community Fairness in Federated Learning via Post-processing](https://mlsanity.com/paper/2405.17782/) (2024)
- [Minimax Optimal Fair Classification with Bounded Demographic Disparity](https://mlsanity.com/paper/2403.18216/) (2024)

## Built on by (most cited first, 2 of 2)

- [FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning](https://mlsanity.com/paper/2506.03777/) (2025)
- [Patient-Conditioned Adaptive Offsets for Reliable Diagnosis across Subgroups](https://mlsanity.com/paper/2601.13094/) (2026)

## 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 .