mlsanityData to 14 Oct 2026

FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data

arXiv 2207.10265 ↗First posted 21 Jul 2022cs.LG cs.CYcited by 6

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) allows agents to jointly train a global model without sharing their local data. However, due to the heterogeneous nature of local data, it is challenging to optimize or even define fairness of the trained global model for the agents. For instance, existing work usually considers accuracy equity as fairness for different agents in FL, which is limited, especially under the heterogeneous setting, since it is intuitively "unfair" to enforce agents with high-quality data to achieve similar accuracy to those who contribute low-quality data, which may discourage the agents from participating in FL. In this work, we propose a formal FL fairness definition, fairness via agent-awareness (FAA), which takes different contributions of heterogeneous agents into account. Under FAA, the performance of agents with high-quality data will not be sacrificed just due to the existence of large amounts of agents with low-quality data. In addition, we propose a fair FL training algorithm based on agent clustering (FOCUS) to achieve fairness in FL measured by FAA. Theoretically, we prove the convergence and optimality of FOCUS under mild conditions for linear and general convex loss functions with bounded smoothness. We also prove that FOCUS always achieves higher fairness in terms of FAA compared with standard FedAvg under both linear and general convex loss functions. Empirically, we show that on four FL datasets, including synthetic data, images, and texts, FOCUS achieves significantly higher fairness in terms of FAA while maintaining competitive prediction accuracy compared with FedAvg and state-of-the-art fair FL algorithms.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 33 of its 54 references that are in the map. First posted on arXiv 21 Jul 2022.

Builds on

33 of 54 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  6. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  7. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  8. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  9. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  10. 2020Federated Learning with Matched Averagingcited by 564
  11. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  12. 2020An Efficient Framework for Clustered Federated Learningcited by 511
21 more
  1. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  2. 2019Agnostic Federated Learningcited by 456
  3. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  4. 2019Fair Resource Allocation in Federated Learningcited by 394
  5. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  6. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  7. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  8. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
  9. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  10. 2014Statistical guarantees for the EM algorithm: From population to sample-based analysiscited by 133
  11. 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 113
  12. 2021Federated Learning with Fair Averagingcited by 61
  13. 2021FedSoft: Soft Clustered Federated Learning with Proximal Local Updatingcited by 46
  14. 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
  15. 2019Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approachcited by 45
  16. 2022Towards Federated Clustering: A Federated Fuzzy c-Means Algorithm (FFCM)cited by 30
  17. 2020Hierarchically Fair Federated Learningcited by 28
  18. 2021Stronger Privacy for Federated Collaborative Filtering with Implicit Feedbackcited by 26
  19. 2021Training Fair Models in Federated Learning without Data Privacy Infringementcited by 26
  20. 2021Scalable federated machine learning with FEDncited by 16
  21. 2021Models of fairness in federated learningcited by 8

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 2.

6 papers.

  1. 2024FedFair^3: Unlocking Threefold Fairness in Federated Learningcited by 5
  2. 2023Entropy-driven Fair and Effective Federated Learningcited by 4
  3. 2024Federated Fairness Analytics: Quantifying Fairness in Federated Learningcited by 4
  4. 2023On the Vulnerability of Fairness Constrained Learning to Malicious Noisecited by 3
  5. 2025Achieving Distributive Justice in Federated Learning via Uncertainty Quantificationcited by 2
  6. 2025Fairness in Federated Learning: Fairness for Whom?cited by 1