mlsanityData to 7 Oct 2026

Personalized Federated Learning via Variational Bayesian Inference

arXiv 2206.07977 ↗First posted 16 Jun 2022cs.LGcited by 68

Not on the map. Why?

Abstract (arXiv)

Federated learning faces huge challenges from model overfitting due to the lack of data and statistical diversity among clients. To address these challenges, this paper proposes a novel personalized federated learning method via Bayesian variational inference named pFedBayes. To alleviate the overfitting, weight uncertainty is introduced to neural networks for clients and the server. To achieve personalization, each client updates its local distribution parameters by balancing its construction error over private data and its KL divergence with global distribution from the server. Theoretical analysis gives an upper bound of averaged generalization error and illustrates that the convergence rate of the generalization error is minimax optimal up to a logarithmic factor. Experiments show that the proposed method outperforms other advanced personalized methods on personalized models, e.g., pFedBayes respectively outperforms other SOTA algorithms by 1.25%, 0.42% and 11.71% on MNIST, FMNIST and CIFAR-10 under non-i.i.d. limited data.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 16 Jun 2022.

Builds on

37 of 56 references.

References · 37

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  7. 2016Variational Inference: A Review for Statisticianscited by 1,466
  8. 2017Federated Multi-Task Learningcited by 669
  9. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  10. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  11. 2015Weight Uncertainty in Neural Networkscited by 554
  12. 2019Federated Learning with Personalization Layerscited by 533
25 more
  1. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
  2. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  3. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  4. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  5. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  6. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
  7. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  8. 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 178
  9. 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
  10. 2019Practical Deep Learning with Bayesian Principlescited by 158
  11. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 154
  12. 2019One-Shot Federated Learningcited by 124
  13. 2020Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithmscited by 78
  14. 2020FedDANE: A Federated Newton-Type Methodcited by 76
  15. 2021Personalized Federated Learning with Gaussian Processescited by 76
  16. 2017Concentration of tempered posteriors and of their variational approximationscited by 66
  17. 2018Posterior Concentration for Sparse Deep Learningcited by 50
  18. 2021A Bayesian Federated Learning Framework with Online Laplace Approximationcited by 41
  19. 2020Efficient Variational Inference for Sparse Deep Learning with Theoretical Guaranteecited by 37
  20. 2019Convergence Rates of Variational Inference in Sparse Deep Learningcited by 27
  21. 2022Federated Learning with Position-Aware Neuronscited by 24
  22. 2017On Statistical Optimality of Variational Bayescited by 21
  23. 2019Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learningcited by 18
  24. 2018Consistency of Variational Bayes Inference for Estimation and Model Selection in Mixturescited by 17
  25. 2022Sparse Federated Learning with Hierarchical Personalized Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 21; 2024: 25; 2025: 12; 2026: 5.

68 papers.

Sort:

By area:

  1. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  2. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  3. 2023Towards Personalized Federated Learning via Heterogeneous Model Reassemblycited by 31
  4. 2023Bayesian Federated Learning: A Surveycited by 22
  5. 2023Confidence-aware Personalized Federated Learning via Variational Expectation Maximizationcited by 17
  6. 2023FedBone: Towards Large-Scale Federated Multi-Task Learningcited by 14
  7. 2024Modeling Inter-Intra Heterogeneity for Graph Federated Learningcited by 12
  8. 2024FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Datacited by 10
  9. 2024Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimationcited by 9
  10. 2023FedHB: Hierarchical Bayesian Federated Learningcited by 8
  11. 2023PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learningcited by 8
  12. 2024A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applicationscited by 8
38 more
  1. 2024Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learningcited by 7
  2. 2024MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classescited by 7
  3. 2022How to Combine Variational Bayesian Networks in Federated Learningcited by 5
  4. 2023Federated Learning via Variational Bayesian Inference: Personalization, Sparsity and Clusteringcited by 5
  5. 2024Personalized Federated Learning of Probabilistic Models: A PAC-Bayesian Approachcited by 5
  6. 2024Rethinking Personalized Federated Learning with Clustering-based Dynamic Graph Propagationcited by 5
  7. 2022Avoid Overfitting User Specific Information in Federated Keyword Spottingcited by 4
  8. 2022Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networkscited by 4
  9. 2023Federated Variational Inference Methods for Structured Latent Variable Modelscited by 4
  10. 2023FedBIAD: Communication-Efficient and Accuracy-Guaranteed Federated Learning with Bayesian Inference-Based Adaptive Dropoutcited by 4
  11. 2024FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantificationcited by 4
  12. 2024Federated Bayesian Deep Learning: The Application of Statistical Aggregation Methods to Bayesian Modelscited by 3
  13. 2024Federated Neural Nonparametric Point Processescited by 3
  14. 2024A Bayesian Framework for Clustered Federated Learningcited by 3
  15. 2025Personalized Language Model Learning on Text Data Without User Identifierscited by 3
  16. 2023Federated Variational Inference: Towards Improved Personalization and Generalizationcited by 2
  17. 2023Privacy Preserving Bayesian Federated Learning in Heterogeneous Settingscited by 2
  18. 2023Federated Neuro-Symbolic Learningcited by 2
  19. 2023Federated PAC-Bayesian Learning on Non-IID datacited by 2
  20. 2023Bayesian Personalized Federated Learning with Shared and Personalized Uncertainty Representationscited by 2
  21. 2023Federated Learning with Nonvacuous Generalisation Boundscited by 2
  22. 2023Federated learning-outcome prediction with multi-layer privacy protectioncited by 2
  23. 2024Future-Proofing Medical Imaging with Privacy-Preserving Federated Learning and Uncertainty Quantification: A Reviewcited by 2
  24. 2024Asymmetrical Reciprocity-based Federated Learning for Resolving Disparities in Medical Diagnosiscited by 2
  25. 2022Tensor Decomposition based Personalized Federated Learningcited by 1
  26. 2022Personalized Federated Learning with Hidden Information on Personalized Priorcited by 1
  27. 2023Personalized Federated Learning via Amortized Bayesian Meta-Learningcited by 1
  28. 2023Distributed Variational Inference for Online Supervised Learningcited by 1
  29. 2023PPFL: A Personalized Federated Learning Framework for Heterogeneous Populationcited by 1
  30. 2024Trustworthy Personalized Bayesian Federated Learning via Posterior Fine-Tunecited by 1
  31. 2024Bayesian Federated Model Compression for Communication and Computation Efficiencycited by 1
  32. 2024FedMAP: Personalised Federated Learning for Real Large-Scale Healthcare Systemscited by 1
  33. 2024Semi-Variance Reduction for Fair Federated Learningcited by 1
  34. 2024Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimizationcited by 1
  35. 2024Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regressioncited by 1
  36. 2024Information-Geometric Barycenters for Bayesian Federated Learningcited by 1
  37. 2025Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Frameworkcited by 1
  38. 2025Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregationcited by 1

50 most cited of 68 All 68 (JSON)