mlsanityData to 7 Oct 2026

Enforcing fairness in private federated learning via the modified method of differential multipliers

arXiv 2109.08604 ↗First posted 17 Sep 2021cs.LG stat.MLcited by 38

Not on the map. Why?

Abstract (arXiv)

Federated learning with differential privacy, or private federated learning, provides a strategy to train machine learning models while respecting users' privacy. However, differential privacy can disproportionately degrade the performance of the models on under-represented groups, as these parts of the distribution are difficult to learn in the presence of noise. Existing approaches for enforcing fairness in machine learning models have considered the centralized setting, in which the algorithm has access to the users' data. This paper introduces an algorithm to enforce group fairness in private federated learning, where users' data does not leave their devices. First, the paper extends the modified method of differential multipliers to empirical risk minimization with fairness constraints, thus providing an algorithm to enforce fairness in the central setting. Then, this algorithm is extended to the private federated learning setting. The proposed algorithm, textttFPFL, is tested on a federated version of the Adult dataset and an "unfair" version of the FEMNIST dataset. The experiments on these datasets show how private federated learning accentuates unfairness in the trained models, and how FPFL is able to mitigate such unfairness.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 32 of its 52 references that are in the map. First posted on arXiv 17 Sep 2021.

Builds on

32 of 52 references.

References · 32

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  7. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  8. 2018LEAF: A Benchmark for Federated Settingscited by 780
  9. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  10. 2017Renyi Differential Privacycited by 643
  11. 2018A Reductions Approach to Fair Classificationcited by 585
  12. 2019Agnostic Federated Learningcited by 451
20 more
  1. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  2. 2019Fair Resource Allocation in Federated Learningcited by 389
  3. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  4. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  5. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 234
  6. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  7. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  8. 2020Fairness-aware Agnostic Federated Learningcited by 87
  9. 2018A General Approach to Adding Differential Privacy to Iterative Training Procedurescited by 84
  10. 2018Differentially Private Fair Learningcited by 76
  11. 2018Private Selection from Private Candidatescited by 75
  12. 2020Lagrangian Duality for Constrained Deep Learningcited by 72
  13. 2020Mitigating Bias in Federated Learningcited by 56
  14. 2020Differentially Private and Fair Deep Learning: A Lagrangian Dual Approachcited by 53
  15. 2020Federated Learning Meets Multi-objective Optimizationcited by 50
  16. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
  17. 2020Improving on-device speaker verification using federated learning with privacycited by 29
  18. 2020Fairness and Accuracy in Federated Learningcited by 27
  19. 2020Differentially Private and Fair Classification via Calibrated Functional Mechanismcited by 20
  20. 2020A Variational Approach to Privacy and Fairnesscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 10; 2024: 15; 2025: 6; 2026: 1.

38 papers.

Sort:

By area:

  1. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  2. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
  3. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 50
  4. 2021Improving Fairness via Federated Learningcited by 39
  5. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  6. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  7. 2022PrivFairFL: Privacy-Preserving Group Fairness in Federated Learningcited by 13
  8. 2022Fair Federated Learning via Bounded Group Losscited by 12
  9. 2023Mitigating Group Bias in Federated Learning: Beyond Local Fairnesscited by 10
  10. 2023Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decompositioncited by 10
  11. 2022FedDAR: Federated Domain-Aware Representation Learningcited by 8
  12. 2024pfl-research: simulation framework for accelerating research in Private Federated Learningcited by 8
26 more
  1. 2024Trust the Process: Zero-Knowledge Machine Learning to Enhance Trust in Generative AI Interactionscited by 6
  2. 2023Mitigating Group Bias in Federated Learning for Heterogeneous Devicescited by 5
  3. 2024GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learningcited by 5
  4. 2024PraFFL: A Preference-Aware Scheme in Fair Federated Learningcited by 5
  5. 2024Achieving Fairness Across Local and Global Models in Federated Learningcited by 5
  6. 2023Federated Learning with Convex Global and Local Constraintscited by 4
  7. 2023Multi-dimensional Fair Federated Learningcited by 4
  8. 2024Post-Fair Federated Learning: Achieving Group and Community Fairness in Federated Learning via Post-processingcited by 4
  9. 2024PUFFLE: Balancing Privacy, Utility, and Fairness in 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. 2023FedGeo: Privacy-Preserving User Next Location Prediction with Federated Learningcited by 3
  13. 2024A Unified View of Group Fairness Tradeoffs Using Partial Information Decompositioncited by 3
  14. 2024Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectivescited by 3
  15. 2023Fairness-aware Federated Minimax Optimization with Convergence Guaranteecited by 2
  16. 2024Federated Fairness without Access to Sensitive Groupscited by 2
  17. 2025AFed: Algorithmic Fair Federated Learningcited by 2
  18. 2024Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clusteringcited by 1
  19. 2025pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learningcited by 1
  20. 2025RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utilitycited by 1
  21. 2025Fairness in Federated Learning: Fairness for Whom?cited by 1
  22. 2024Distribution-Free Fair Federated Learning with Small Samplescited by 0
  23. 2024A Stochastic Optimization Framework for Private and Fair Learning From Decentralized Datacited by 0
  24. 2025Mitigating Group-Level Fairness Disparities in Federated Visual Language Modelscited by 0
  25. 2025FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluationcited by 0
  26. 2026Federated Learning-Assisted Optimization of Mobile Transmission with Digital Twinscited by 0