mlsanityData to 7 Oct 2026

Distribution-Free Fair Federated Learning with Small Samples

arXiv 2402.16158 ↗First posted 25 Feb 2024stat.ML cs.CY cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

As federated learning gains increasing importance in real-world applications due to its capacity for decentralized data training, addressing fairness concerns across demographic groups becomes critically important. However, most existing machine learning algorithms for ensuring fairness are designed for centralized data environments and generally require large-sample and distributional assumptions, underscoring the urgent need for fairness techniques adapted for decentralized and heterogeneous systems with finite-sample and distribution-free guarantees. To address this issue, this paper introduces FedFaiREE, a post-processing algorithm developed specifically for distribution-free fair learning in decentralized settings with small samples. Our approach accounts for unique challenges in decentralized environments, such as client heterogeneity, communication costs, and small sample sizes. We provide rigorous theoretical guarantees for both fairness and accuracy, and our experimental results further provide robust empirical validation for our proposed method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 25 Feb 2024.

Builds on

29 of 43 references.

References · 29

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  4. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  5. 2018A Reductions Approach to Fair Classificationcited by 585
  6. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  7. 2017Algorithmic decision making and the cost of fairnesscited by 402
  8. 2020Fairness in Machine Learning: A Surveycited by 369
  9. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  10. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
  11. 2018Why Is My Classifier Discriminatory?cited by 143
  12. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
17 more
  1. 2020Collaborative Fairness in Federated Learningcited by 95
  2. 2016A Confidence-Based Approach for Balancing Fairness and Accuracycited by 73
  3. 2016Satisfying Real-world Goals with Dataset Constraintscited by 68
  4. 2020An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guaranteecited by 61
  5. 2021It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarkscited by 61
  6. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
  7. 2023Federated Conformal Predictors for Distributed Uncertainty Quantificationcited by 46
  8. 2021Improving Fairness via Federated Learningcited by 39
  9. 2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
  10. 2022Federated Learning for Healthcare Domain - Pipeline, Applications and Challengescited by 34
  11. 2023Conformal Prediction for Federated Uncertainty Quantification Under Label Shiftcited by 29
  12. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  13. 2022Bayes-Optimal Classifiers under Group Fairnesscited by 24
  14. 2022Fair Federated Learning via Bounded Group Losscited by 12
  15. 2023ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Modelscited by 9
  16. 2023SimFair: A Unified Framework for Fairness-Aware Multi-Label Classificationcited by 7
  17. 2022FaiREE: Fair Classification with Finite-Sample and Distribution-Free Guaranteecited by 5

Built on by

Not cited yet.