Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation
Not on the map. Why?
Abstract (arXiv)
Personalized Bayesian federated learning (PBFL) handles non-i.i.d. client data and quantifies uncertainty by combining personalization with Bayesian inference. However, existing PBFL methods face two limitations: restrictive parametric assumptions in client posterior inference and naive parameter averaging for server aggregation. To overcome these issues, we propose FedWBA, a novel PBFL method that enhances both local inference and global aggregation. At the client level, we use particle-based variational inference for nonparametric posterior representation. At the server level, we introduce particle-based Wasserstein barycenter aggregation, offering a more geometrically meaningful approach. Theoretically, we provide local and global convergence guarantees for FedWBA. Locally, we prove a KL divergence decrease lower bound per iteration for variational inference convergence. Globally, we show that the Wasserstein barycenter converges to the true parameter as the client data size increases. Empirically, experiments show that FedWBA outperforms baselines in prediction accuracy, uncertainty calibration, and convergence rate, with ablation studies confirming its robustness.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 37 of its 54 references that are in the map. First posted on arXiv 20 May 2025.
Builds on
37 of 54 references.
References · 37
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2016Variational Inference: A Review for Statisticianscited by 1,472
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
- 2020The Future of Digital Health with Federated Learningcited by 633
- 2020Personalized Federated Learning with Moreau Envelopescited by 618
- 2019Federated Learning with Personalization Layerscited by 541
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
- 2020An Efficient Framework for Clustered Federated Learningcited by 511
25 more
- 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
- 2021Towards Personalized Federated Learningcited by 464
- 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
- 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 269
- 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
- 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
- 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
- 2021Federated Learning for Open Bankingcited by 141
- 2020Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithmscited by 78
- 2021Personalized Federated Learning with Gaussian Processescited by 76
- 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
- 2019Federated Learning with Bayesian Differential Privacycited by 60
- 2015Scalable Bayes via Barycenter in Wasserstein Spacecited by 44
- 2021A Bayesian Federated Learning Framework with Online Laplace Approximationcited by 41
- 2020Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descentcited by 35
- 2019Federated User Representation Learningcited by 32
- 2023Bayesian Federated Learning: A Surveycited by 22
- 2023Federated Learning as Variational Inference: A Scalable Expectation Propagation Approachcited by 17
- 2023Confidence-aware Personalized Federated Learning via Variational Expectation Maximizationcited by 17
- 2022Federated Learning with Uncertainty via Distilled Predictive Distributionscited by 12
- 2023FedHB: Hierarchical Bayesian Federated Learningcited by 8
- 2022How to Combine Variational Bayesian Networks in Federated Learningcited by 5
- 2024Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regressioncited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.