mlsanityData to 7 Oct 2026

Federated Learning with Fair Averaging

arXiv 2104.14937 ↗First posted 30 Apr 2021cs.LGcited by 59

Not on the map. Why?

Abstract (arXiv)

Fairness has emerged as a critical problem in federated learning (FL). In this work, we identify a cause of unfairness in FL -- conflicting gradients with large differences in the magnitudes. To address this issue, we propose the federated fair averaging (FedFV) algorithm to mitigate potential conflicts among clients before averaging their gradients. We first use the cosine similarity to detect gradient conflicts, and then iteratively eliminate such conflicts by modifying both the direction and the magnitude of the gradients. We further show the theoretical foundation of FedFV to mitigate the issue conflicting gradients and converge to Pareto stationary solutions. Extensive experiments on a suite of federated datasets confirm that FedFV compares favorably against state-of-the-art methods in terms of fairness, accuracy and efficiency. The source code is available at https://github.com/WwZzz/easyFL.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 23 of its 39 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

23 of 39 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  5. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  7. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  8. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  9. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  10. 2018LEAF: A Benchmark for Federated Settingscited by 780
  11. 2019Agnostic Federated Learningcited by 451
  12. 2019Fair Resource Allocation in Federated Learningcited by 389
11 more
  1. 2019Orthogonal Gradient Descent for Continual Learningcited by 361
  2. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 303
  3. 2020Survey of Personalization Techniques for Federated Learningcited by 144
  4. 2018Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithmscited by 106
  5. 2020Collaborative Fairness in Federated Learningcited by 95
  6. 2020Mitigating Bias in Federated Learningcited by 56
  7. 2020Federated Learning Meets Multi-objective Optimizationcited by 50
  8. 2020Bandit-based Communication-Efficient Client Selection Strategies for Federated Learningcited by 29
  9. 2020Fairness and Accuracy in Federated Learningcited by 27
  10. 2019Improved Schemes for Episodic Memory-based Lifelong Learningcited by 7
  11. 2019Towards Fair and Privacy-Preserving Federated Deep Modelscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 7; 2023: 12; 2024: 18; 2025: 13; 2026: 6.

59 papers.

Sort:

By area:

  1. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
  2. 2021Towards Fairness-Aware Federated Learningcited by 57
  3. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  4. 2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 28
  5. 2024A Systematic Review on Long-Tailed Learningcited by 27
  6. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  7. 2023No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendationcited by 18
  8. 2023Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methodscited by 17
  9. 2021Unified Group Fairness on Federated Learningcited by 15
  10. 2024Federated Unlearning with Gradient Descent and Conflict Mitigationcited by 15
  11. 2023FLGo: A Fully Customizable Federated Learning Platformcited by 12
  12. 2024AdaFed: Fair Federated Learning via Adaptive Common Descent Directioncited by 12
38 more
  1. 2024Federated Graph Learning for Cross-Domain Recommendationcited by 9
  2. 2023FedSampling: A Better Sampling Strategy for Federated Learningcited by 8
  3. 2024Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutionscited by 8
  4. 2022FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learningcited by 7
  5. 2025Federated Learning with Domain Shift Erasercited by 7
  6. 2022A Fair Federated Learning Framework With Reinforcement Learningcited by 6
  7. 2022FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Datacited by 6
  8. 2023CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled Regularizationcited by 5
  9. 2024PraFFL: A Preference-Aware Scheme in Fair Federated Learningcited by 5
  10. 2023Entropy-driven Fair and Effective Federated Learningcited by 4
  11. 2023Federated Learning for 6G: Paradigms, Taxonomy, Recent Advances and Insightscited by 4
  12. 2024PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learningcited by 4
  13. 2024Federated Fairness Analytics: Quantifying Fairness in Federated Learningcited by 4
  14. 2024Adaptive Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Learningcited by 4
  15. 2025Distributed Quasi-Newton Method for Fair and Fast Federated Learningcited by 4
  16. 2023Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Datacited by 3
  17. 2024Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectivescited by 3
  18. 2024Contribution Evaluation of Heterogeneous Participants in Federated Learning via Prototypical Representationscited by 3
  19. 2024FedDP: Privacy-preserving method based on federated learning for histopathology image segmentationcited by 3
  20. 2025Fairness in Federated Learning: Trends, Challenges, and Opportunitiescited by 3
  21. 2022Fairness in Federated Learning for Spatial-Temporal Applicationscited by 2
  22. 2023FedDD: Toward Communication-efficient Federated Learning with Differential Parameter Dropoutcited by 2
  23. 2023Federated Learning via Consensus Mechanism on Heterogeneous Data: A New Perspective on Convergencecited by 2
  24. 2025Fairness in Augmented Graph Learning: A Surveycited by 2
  25. 2025FedGA: A Fair Federated Learning Framework Based on the Gini Coefficientcited by 2
  26. 2022FedCAT: Towards Accurate Federated Learning via Device Concatenationcited by 1
  27. 2023Dynamic Fair Federated Learning Based on Reinforcement Learningcited by 1
  28. 2024Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clusteringcited by 1
  29. 2024PFAttack: Stealthy Attack Bypassing Group Fairness in Federated Learningcited by 1
  30. 2024FedMABA: Towards Fair Federated Learning through Multi-Armed Bandits Allocationcited by 1
  31. 2025Achieving Distributive Justice in Federated Learning via Uncertainty Quantificationcited by 1
  32. 2022Federated Geometric Monte Carlo Clustering to Counter Non-IID Datasetscited by 0
  33. 2024Equitable Federated Learning with Activation Clusteringcited by 0
  34. 2024Federated Learning with Relative Fairnesscited by 0
  35. 2025Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learningcited by 0
  36. 2025ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoningcited by 0
  37. 2025Accelerated Training of Federated Learning via Second-Order Methodscited by 0
  38. 2025FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluationcited by 0

50 most cited of 59 All 59 (JSON)