Information-Geometric Barycenters for Bayesian Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) is a widely used and impactful distributed optimization framework that achieves consensus through averaging locally trained models. While effective, this approach may not align well with Bayesian inference, where the model space has the structure of a distribution space. Taking an information-geometric perspective, we reinterpret FL aggregation as the problem of finding the barycenter of local posteriors using a prespecified divergence metric, minimizing the average discrepancy across clients. This perspective provides a unifying framework that generalizes many existing methods and offers crisp insights into their theoretical underpinnings. We then propose BA-BFL, an algorithm that retains the convergence properties of Federated Averaging in non-convex settings. In non-independent and identically distributed scenarios, we conduct extensive comparisons with statistical aggregation techniques, showing that BA-BFL achieves performance comparable to state-of-the-art methods while offering a geometric interpretation of the aggregation phase. Additionally, we extend our analysis to Hybrid Bayesian Deep Learning, exploring the impact of Bayesian layers on uncertainty quantification and model calibration.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 16 Dec 2024.
Builds on
34 of 47 references.
References · 34
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2016Variational Inference: A Review for Statisticianscited by 1,472
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
- 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
- 2020Personalized Federated Learning with Moreau Envelopescited by 618
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
- 2020Federated Learning with Matched Averagingcited by 564
- 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
- 2020Adaptive Personalized Federated Learningcited by 358
- 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 338
22 more
- 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
- 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
- 2020Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithmscited by 78
- 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 77
- 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
- 2024Variational Learning is Effective for Large Deep Networkscited by 65
- 2023Revisiting Weighted Aggregation in Federated Learning with Neural Networkscited by 58
- 2021A Bayesian Federated Learning Framework with Online Laplace Approximationcited by 41
- 2022FedPop: A Bayesian Approach for Personalised Federated Learningcited by 35
- 2022Fusion of Probability Density Functionscited by 22
- 2023Bayesian Federated Learning: A Surveycited by 22
- 2021GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learningcited by 21
- 2022Proportional Fairness in Federated Learningcited by 21
- 2023Federated Learning as Variational Inference: A Scalable Expectation Propagation Approachcited by 17
- 2023Confidence-aware Personalized Federated Learning via Variational Expectation Maximizationcited by 17
- 2018The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learningcited by 13
- 2018Bayesian Learning with Wasserstein Barycenterscited by 12
- 2022Federated Learning with Uncertainty via Distilled Predictive Distributionscited by 12
- 2024Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimationcited by 9
- 2023FedHB: Hierarchical Bayesian Federated Learningcited by 8
- 2022How to Combine Variational Bayesian Networks in Federated Learningcited by 5
- 2024Federated Bayesian Deep Learning: The Application of Statistical Aggregation Methods to Bayesian Modelscited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.