mlsanityData to 14 Oct 2026

Proportional Fairness in Federated Learning

arXiv 2202.01666 ↗First posted 3 Feb 2022cs.LG cs.AI math.OCcited by 21

Not on the map. Why?

Abstract (arXiv)

With the increasingly broad deployment of federated learning (FL) systems in the real world, it is critical but challenging to ensure fairness in FL, i.e. reasonably satisfactory performances for each of the numerous diverse clients. In this work, we introduce and study a new fairness notion in FL, called proportional fairness (PF), which is based on the relative change of each client's performance. From its connection with the bargaining games, we propose PropFair, a novel and easy-to-implement algorithm for finding proportionally fair solutions in FL and study its convergence properties. Through extensive experiments on vision and language datasets, we demonstrate that PropFair can approximately find PF solutions, and it achieves a good balance between the average performances of all clients and of the worst 10% clients. Our code is available at urlhttps://github.com/huawei-noah/Federated-Learning/tree/main/FairFL.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 33 of its 79 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

33 of 79 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2021Convex optimizationcited by 2,515
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  6. 2018Group Normalizationcited by 1,524
  7. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  8. 2020Adaptive Federated Optimizationcited by 1,046
  9. 2017Counterfactual Fairnesscited by 804
  10. 2018LEAF: A Benchmark for Federated Settingscited by 792
  11. 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 724
  12. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
21 more
  1. 2020Federated Learning with Matched Averagingcited by 564
  2. 2019Agnostic Federated Learningcited by 456
  3. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  4. 2017On Fairness and Calibrationcited by 406
  5. 2019Fair Resource Allocation in Federated Learningcited by 394
  6. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  7. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 305
  8. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 300
  9. 2020Fairness in Machine Learningcited by 194
  10. 2019Federated Evaluation of On-device Personalizationcited by 147
  11. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  12. 2021Federated Learning for Open Bankingcited by 141
  13. 2020A Principled Approach to Data Valuation for Federated Learningcited by 127
  14. 2020FedSplit: An algorithmic framework for fast federated optimizationcited by 108
  15. 2020Tilted Empirical Risk Minimizationcited by 106
  16. 2019Reliable Federated Learning for Mobile Networkscited by 92
  17. 2020Federated Learning Meets Multi-objective Optimizationcited by 53
  18. 2021On Tilted Losses in Machine Learning: Theory and Applicationscited by 43
  19. 2019R'enyi Fair Inferencecited by 33
  20. 2021GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learningcited by 21
  21. 2020Beyond Individual and Group Fairnesscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 12; 2025: 3; 2026: 1.

21 papers.

Sort:

By area:

  1. 2024Fair Resource Allocation in Multi-Task Learningcited by 35
  2. 2024Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedbackcited by 32
  3. 2024Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learningcited by 9
  4. 2023Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learningcited by 8
  5. 2023Scaff-PD: Communication Efficient Fair and Robust Federated Learningcited by 6
  6. 2024Achieving Fairness Across Local and Global Models in Federated Learningcited by 5
  7. 2023Entropy-driven Fair and Effective Federated Learningcited by 4
  8. 2023Federated Learning Under Restricted User Availabilitycited by 4
  9. 2024Differentially Private Clustered Federated Learningcited by 4
  10. 2024Generalization and Robustness of the Tilted Empirical Riskcited by 4
  11. 2024Adaptive Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Learningcited by 4
  12. 2023Understanding the Role of Layer Normalization in Label-Skewed Federated Learningcited by 2
9 more
  1. 2024Pursuing Overall Welfare in Federated Learning through Sequential Decision Makingcited by 2
  2. 2025Achieving Distributive Justice in Federated Learning via Uncertainty Quantificationcited by 2
  3. 2024Predicting Infant Brain Connectivity with Federated Multi-Trajectory GNNs using Scarce Datacited by 1
  4. 2024Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clusteringcited by 1
  5. 2024FedMABA: Towards Fair Federated Learning through Multi-Armed Bandits Allocationcited by 1
  6. 2024Information-Geometric Barycenters for Bayesian Federated Learningcited by 1
  7. 2025A Flexible Fairness Framework with Surrogate Loss Reweighting for Addressing Sociodemographic Disparitiescited by 0
  8. 2025Cost-Free Personalization via Information-Geometric Projection in Bayesian Federated Learningcited by 0
  9. 2026FUSE: Fairness-aware Update Screening against Byzantine Exploitation in q-Fair Federated Learningcited by 0