mlsanityData to 7 Oct 2026

Improving Fairness via Federated Learning

arXiv 2110.15545 ↗First posted 29 Oct 2021cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

Recently, lots of algorithms have been proposed for learning a fair classifier from decentralized data. However, many theoretical and algorithmic questions remain open. First, is federated learning necessary, i.e., can we simply train locally fair classifiers and aggregate them? In this work, we first propose a new theoretical framework, with which we demonstrate that federated learning can strictly boost model fairness compared with such non-federated algorithms. We then theoretically and empirically show that the performance tradeoff of FedAvg-based fair learning algorithms is strictly worse than that of a fair classifier trained on centralized data. To bridge this gap, we propose FedFB, a private fair learning algorithm on decentralized data. The key idea is to modify the FedAvg protocol so that it can effectively mimic the centralized fair learning. Our experimental results show that FedFB significantly outperforms existing approaches, sometimes matching the performance of the centrally trained model.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 29 Oct 2021.

Builds on

22 of 38 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  5. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  6. 2019Agnostic Federated Learningcited by 451
  7. 2019Fair Resource Allocation in Federated Learningcited by 389
  8. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 381
  9. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  10. 2019Identifying and Correcting Label Bias in Machine Learningcited by 146
  11. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  12. 2019One-Shot Federated Learningcited by 124
10 more
  1. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
  2. 2020FairBatch: Batch Selection for Model Fairnesscited by 99
  3. 2020Collaborative Fairness in Federated Learningcited by 95
  4. 2020Fairness-aware Agnostic Federated Learningcited by 87
  5. 2017From Parity to Preference-based Notions of Fairness in Classificationcited by 60
  6. 2020FR-Train: A Mutual Information-Based Approach to Fair and Robust Trainingcited by 52
  7. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
  8. 2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
  9. 2020Hierarchically Fair Federated Learningcited by 28
  10. 2021Training Fair Models in Federated Learning without Data Privacy Infringementcited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 11; 2024: 10; 2025: 8; 2026: 2.

39 papers.

Sort:

  1. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 50
  2. 2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 28
  3. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  4. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  5. 2022Fairness in Federated Learning via Core-Stabilitycited by 22
  6. 2023Achieving Linear Speedup in Non-IID Federated Bilevel Learningcited by 18
  7. 2023Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methodscited by 17
  8. 2023SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learningcited by 14
  9. 2022Fair Federated Learning via Bounded Group Losscited by 12
  10. 2023Bias Propagation in Federated Learningcited by 12
  11. 2022FAIR-FATE: Fair Federated Learning with Momentumcited by 10
  12. 2023Mitigating Group Bias in Federated Learning: Beyond Local Fairnesscited by 10
27 more
  1. 2023Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decompositioncited by 10
  2. 2021Federated Gaussian Process: Convergence, Automatic Personalization and Multi-fidelity Modelingcited by 8
  3. 2021Models of fairness in federated learningcited by 8
  4. 2022FedDAR: Federated Domain-Aware Representation Learningcited by 8
  5. 2023Mitigating Group Bias in Federated Learning for Heterogeneous Devicescited by 5
  6. 2024GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learningcited by 5
  7. 2024PraFFL: A Preference-Aware Scheme in Fair Federated Learningcited by 5
  8. 2024Achieving Fairness Across Local and Global Models in Federated Learningcited by 5
  9. 2023Multi-dimensional Fair Federated Learningcited by 4
  10. 2024Federated Fairness Analytics: Quantifying Fairness in Federated Learningcited by 4
  11. 2024EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learningcited by 4
  12. 2023Fairness-aware Federated Minimax Optimization with Convergence Guaranteecited by 2
  13. 2023Equipping Federated Graph Neural Networks with Structure-aware Group Fairnesscited by 2
  14. 2025AFed: Algorithmic Fair Federated Learningcited by 2
  15. 2025The Cost of Local and Global Fairness in Federated Learningcited by 2
  16. 2024CurvFed: Curvature-Aligned Federated Learning for Fairness without Demographicscited by 1
  17. 2024Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clusteringcited by 1
  18. 2025pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learningcited by 1
  19. 2025LoGoFair: Post-Processing for Local and Global Fairness in Federated Learningcited by 1
  20. 2024Distribution-Free Fair Federated Learning with Small Samplescited by 0
  21. 2024WassFFed: Wasserstein Fair Federated Learningcited by 0
  22. 2025Towards Trustworthy Federated Learningcited by 0
  23. 2025Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learningcited by 0
  24. 2025FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learningcited by 0
  25. 2025FAIRVAR: Fair Federated Learning via Variance Regularizationcited by 0
  26. 2026When the Server Steps In: Calibrated Updates for Fair Federated Learningcited by 0
  27. 2026Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learningcited by 0