mlsanityData to 14 Oct 2026

Bias Propagation in Federated Learning

arXiv 2309.02160 ↗First posted 5 Sep 2023cs.LG cs.CY stat.MLcited by 12

Not on the map. Why?

Abstract (arXiv)

We show that participating in federated learning can be detrimental to group fairness. In fact, the bias of a few parties against under-represented groups (identified by sensitive attributes such as gender or race) can propagate through the network to all the parties in the network. We analyze and explain bias propagation in federated learning on naturally partitioned real-world datasets. Our analysis reveals that biased parties unintentionally yet stealthily encode their bias in a small number of model parameters, and throughout the training, they steadily increase the dependence of the global model on sensitive attributes. What is important to highlight is that the experienced bias in federated learning is higher than what parties would otherwise encounter in centralized training with a model trained on the union of all their data. This indicates that the bias is due to the algorithm. Our work calls for auditing group fairness in federated learning and designing learning algorithms that are robust to bias propagation.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 39 of its 56 references that are in the map. First posted on arXiv 5 Sep 2023.

Builds on

39 of 56 references.

References · 39

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  7. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  8. 2020Adaptive Federated Optimizationcited by 1,046
  9. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  10. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  11. 2020The Future of Digital Health with Federated Learningcited by 633
  12. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
27 more
  1. 2019Agnostic Federated Learningcited by 456
  2. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 449
  3. 2019Fair Resource Allocation in Federated Learningcited by 394
  4. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  5. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 364
  6. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 300
  7. 2019BCN20000: Dermoscopic Lesions in the Wildcited by 225
  8. 2018A comparative study of fairness-enhancing interventions in machine learningcited by 208
  9. 2020Mime: Mimicking Centralized Stochastic Algorithms in Federated Learningcited by 154
  10. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
  11. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 118
  12. 2021Distributionally Robust Federated Averagingcited by 104
  13. 2020Collaborative Fairness in Federated Learningcited by 95
  14. 2020Fairness-aware Agnostic Federated Learningcited by 87
  15. 2019Conditional Learning of Fair Representationscited by 78
  16. 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
  17. 2020How Do Fair Decisions Fare in Long-term Qualification?cited by 60
  18. 2020Mitigating Bias in Federated Learningcited by 56
  19. 2019Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?cited by 50
  20. 2021Improving Fairness via Federated Learningcited by 39
  21. 2021Fair Representation Learning for Heterogeneous Information Networkscited by 28
  22. 2021Training Fair Models in Federated Learning without Data Privacy Infringementcited by 26
  23. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  24. 2022Marrying Fairness and Explainability in Supervised Learningcited by 23
  25. 2022Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learningcited by 11
  26. 2021Federating for Learning Group Fair Modelscited by 9
  27. 2019Bias In, Bias Out? Evaluating the Folk Wisdomcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 4; 2026: 3.

12 papers.

  1. 2024Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspectivecited by 6
  2. 2024Achieving Fairness Across Local and Global Models in Federated Learningcited by 5
  3. 2024Enhancing Mental Health Support through Human-AI Collaboration: Toward Secure and Empathetic AI-enabled chatbotscited by 5
  4. 2024Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learningcited by 4
  5. 2025Fairness-Constrained Optimization Attack in Federated Learningcited by 1
  6. 2024WassFFed: Wasserstein Fair Federated Learningcited by 0
  7. 2025Benchmarking Mutual Information-based Loss Functions in Federated Learningcited by 0
  8. 2025FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learningcited by 0
  9. 2025FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluationcited by 0
  10. 2026When the Server Steps In: Calibrated Updates for Fair Federated Learningcited by 0
  11. 2026Rashomon Sets and Model Multiplicity in Federated Learningcited by 0
  12. 2026Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learningcited by 0