Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning
Hong-You Chen, Wei-Lun Chao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace weight averaging with Bayesian model sampling, ensemble, and server-side distillation | Federated learning · CIFAR-10, non-i.i.d. Step, ResNet20 | test accuracy (%): 70.2$\pm$0.17 -> 77.5$\pm$0.42 | Improved |
| Add SWA to ensemble distillation (ablation) | FedBE · CIFAR-10, non-i.i.d. Step, ResNet20 | test accuracy (%): 74.9$\pm$1.41 -> 77.5$\pm$0.42 | Improved |
| Add sampled global models to ensemble distillation targets (ablation) | FedBE · CIFAR-10, non-i.i.d. Step, ConvNet | test accuracy (%): 72.6$\pm$0.28 -> 73.1$\pm$0.46 | Improved |
| Combine sampled models, client weight average, and client models as distillation targets (ablation) | FedBE · CIFAR-10, non-i.i.d. Step, ConvNet | test accuracy (%): 74.0$\pm$0.66 -> 74.5$\pm$0.51 | Improved |
| Replace SWA with SGD for Bayesian ensemble distillation (ablation) | FedBE · CIFAR-10, non-i.i.d. Step, ConvNet, one-round | test accuracy (%): 35.7$\pm$0.86 -> 35.1$\pm$0.76 | Hurt |
| Sample models from the Bayesian distribution rather than ensemble only client models (ablation) | Model ensemble · CIFAR-10, non-i.i.d. Step, ConvNet, one-round | test accuracy (%): 60.5$\pm$0.28 -> 62.5$\pm$0.35 | Improved |
| Use out-of-domain CIFAR-100 or Tiny-ImageNet unlabeled data instead of CIFAR-10 server data (ablation) | FedBE · CIFAR-10, non-i.i.d. Step | test accuracy (%): 74.5$\pm$0.51; 74.4$\pm$0.45; 74.5$\pm$0.64 | No clear effect |
| Increase the amount of unlabeled server data (ablation) | FedBE · CIFAR-10, non-i.i.d. Step | test accuracy (%) | Improved |
| Add FedBE aggregation to FedProx | FedProx · CIFAR-10, non-i.i.d. Step, ResNet20 | test accuracy (%): 71.1$\pm$0.52 -> 77.7$\pm$0.45 | Improved |
| Add FedBE aggregation to FedAvgM | FedAvgM · CIFAR-10, non-i.i.d. Step, ResNet20 | test accuracy (%): 73.2$\pm$0.57 -> 78.0$\pm$0.46 | Improved |
| Replace batch normalization with group normalization (ablation) | FedAvg ResNet20 · CIFAR-10, non-i.i.d. Step, 200 rounds | test accuracy (%): 74.6% -> 76.4% | Improved |
| Apply FedBE aggregation to SCAFFOLD | SCAFFOLD · CIFAR-10, non-i.i.d. Step, ResNet20 | test accuracy (%): 59.4% -> 76.4% | Improved |
Later papers that compared with this method
3 later accepted papers report FedBE as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space (AAAI 2024 · better on 4 of 5 shared results)
- A Bayesian Federated Learning Framework With Online Laplace Approximation (TPAMI 2023 · better on 4 of 4 shared results)
- Revisiting Weighted Aggregation in Federated Learning with Neural Networks (ICML 2023 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FedBEns: One-Shot Federated Learning based on Bayesian Ensemble (ICML 2025 · similarity 0.89)
- Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach (NeurIPS 2024 · similarity 0.87)
- Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space (AAAI 2024 · similarity 0.87)
- Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation (NeurIPS 2025 · similarity 0.87)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.86)
- FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
