FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning

Abstract

Federated learning aims to collaboratively train a strong global model by accessing users' locally trained models but not their own data. A crucial step is therefore to aggregate local models into a global model, which has been shown challenging when users have non-i.i.d. data. In this paper, we propose a novel aggregation algorithm named FedBE, which takes a Bayesian inference perspective by sampling higher-quality global models and combining them via Bayesian model Ensemble, leading to much robust aggregation. We show that an effective model distribution can be constructed by simply fitting a Gaussian or Dirichlet distribution to the local models. Our empirical studies validate FedBE's superior performance, especially when users' data are not i.i.d. and when the neural networks go deeper. Moreover, FedBE is compatible with recent efforts in regularizing users' model training, making it an easily applicable module: you only need to replace the aggregation method but leave other parts of your federated learning algorithm intact. Our code is publicly available at https://github.com/hongyouc/FedBE.

Accepted to ICLR 2021; the camera-ready version with code URL

References in corpus (12)

• Distilling the Knowledge in a Neural Network
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• On Calibration of Modern Neural Networks
• Towards Federated Learning at Scale: System Design
• Ensemble Distillation for Robust Model Fusion in Federated Learning
• FedMD: Heterogenous Federated Learning via Model Distillation
• Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
• On the Convergence of Local Descent Methods in Federated Learning
• One-Shot Federated Learning
• Adaptive Federated Optimization
• Variance Reduced Local SGD with Lower Communication Complexity
• Private Query Release Assisted by Public Data

Cited by in corpus (5)

• Ensemble Distillation for Robust Model Fusion in Federated Learning
• Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentation
• Communication-Efficient Federated Distillation
• Edge Bias in Federated Learning and its Solution by Buffered Knowledge Distillation
• FedRAD: Federated Robust Adaptive Distillation