mlsanityData to 14 Oct 2026

Mitigating Group Bias in Federated Learning for Heterogeneous Devices

arXiv 2309.07085 ↗First posted 13 Sep 2023cs.LG cs.AI cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Federated Learning is emerging as a privacy-preserving model training approach in distributed edge applications. As such, most edge deployments are heterogeneous in nature i.e., their sensing capabilities and environments vary across deployments. This edge heterogeneity violates the independence and identical distribution (IID) property of local data across clients and produces biased global models i.e. models that contribute to unfair decision-making and discrimination against a particular community or a group. Existing bias mitigation techniques only focus on bias generated from label heterogeneity in non-IID data without accounting for domain variations due to feature heterogeneity and do not address global group-fairness property. Our work proposes a group-fair FL framework that minimizes group-bias while preserving privacy and without resource utilization overhead. Our main idea is to leverage average conditional probabilities to compute a cross-domain group textitimportance weights derived from heterogeneous training data to optimize the performance of the worst-performing group using a modified multiplicative weights update method. Additionally, we propose regularization techniques to minimize the difference between the worst and best-performing groups while making sure through our thresholding mechanism to strike a balance between bias reduction and group performance degradation. Our evaluation of human emotion recognition and image classification benchmarks assesses the fair decision-making of our framework in real-world heterogeneous settings.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 50 of its 97 references that are in the map. First posted on arXiv 13 Sep 2023.

Builds on

50 of 97 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  7. 2014Certifying and removing disparate impactcited by 715
  8. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  9. 2017The Implicit Bias of Gradient Descent on Separable Datacited by 655
  10. 2019Agnostic Federated Learningcited by 456
  11. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  12. 2019Fair Resource Allocation in Federated Learningcited by 394
38 more
  1. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  2. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 305
  3. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 251
  4. 2018Multiaccuracy: Black-Box Post-Processing for Fairness in Classificationcited by 222
  5. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 153
  6. 2018Why Is My Classifier Discriminatory?cited by 143
  7. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 118
  8. 2020Tilted Empirical Risk Minimizationcited by 106
  9. 2021Distributionally Robust Federated Averagingcited by 104
  10. 2020Robust Federated Learning: The Case of Affine Distribution Shiftscited by 102
  11. 2019Context-Aware Emotion Recognition Networkscited by 99
  12. 2020FairBatch: Batch Selection for Model Fairnesscited by 99
  13. 2020Collaborative Fairness in Federated Learningcited by 95
  14. 2017On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimizationcited by 92
  15. 2020Fairness-aware Agnostic Federated Learningcited by 87
  16. 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
  17. 2018Bias Mitigation Post-processing for Individual and Group Fairnesscited by 72
  18. 2020Mitigating Bias in Federated Learningcited by 56
  19. 2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
  20. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
  21. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  22. 2018Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Datacited by 39
  23. 2021Improving Fairness via Federated Learningcited by 39
  24. 2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
  25. 2021Game of Gradients: Mitigating Irrelevant Clients in Federated Learningcited by 35
  26. 2021Learning Bounds for Open-Set Learningcited by 27
  27. 2021Training Fair Models in Federated Learning without Data Privacy Infringementcited by 26
  28. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  29. 2021Improving Fairness for Data Valuation in Horizontal Federated Learningcited by 22
  30. 2022FLAIR: Federated Learning Annotated Image Repositorycited by 22
  31. 2021Modeling Techniques for Machine Learning Fairness: A Surveycited by 17
  32. 2023Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methodscited by 17
  33. 2021Unified Group Fairness on Federated Learningcited by 15
  34. 2021New Metrics to Evaluate the Performance and Fairness of Personalized Federated Learningcited by 11
  35. 2021Communication-Efficient Agnostic Federated Averagingcited by 10
  36. 2021Robust Fairness-aware Learning Under Sample Selection Biascited by 9
  37. 2020Multiclass classification by sparse multinomial logistic regressioncited by 3
  38. 2022E2FL: Equal and Equitable Federated Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Riskcited by 2
  2. 2025Fairness in Federated Learning: Fairness for Whom?cited by 1
  3. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  4. 2025FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluationcited by 0
  5. 2026A Drift Stable Quantum Federated Learning for Intelligent Servicescited by 0