Personalized Federated Learning with Hidden Information on Personalized Prior

19 Nov 2022  ·  Mingjia Shi, Yuhao Zhou, Qing Ye, Jiancheng Lv ·

Federated learning (FL for simplification) is a distributed machine learning technique that utilizes global servers and collaborative clients to achieve privacy-preserving global model training without direct data sharing. However, heterogeneous data problem, as one of FL's main problems, makes it difficult for the global model to perform effectively on each client's local data. Thus, personalized federated learning (PFL for simplification) aims to improve the performance of the model on local data as much as possible. Bayesian learning, where the parameters of the model are seen as random variables with a prior assumption, is a feasible solution to the heterogeneous data problem due to the tendency that the more local data the model use, the more it focuses on the local data, otherwise focuses on the prior. When Bayesian learning is applied to PFL, the global model provides global knowledge as a prior to the local training process. In this paper, we employ Bayesian learning to model PFL by assuming a prior in the scaled exponential family, and therefore propose pFedBreD, a framework to solve the problem we model using Bregman divergence regularization. Empirically, our experiments show that, under the prior assumption of the spherical Gaussian and the first order strategy of mean selection, our proposal significantly outcompetes other PFL algorithms on multiple public benchmarks.

PDF Abstract

Results from the Paper


 Ranked #1 on Image Classification on Fashion-MNIST (Accuracy metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification CIFAR-10 pFedBreD_ns_mg Percentage correct 80.63 # 214
Image Classification Fashion-MNIST pFedBreD_ns_mg Accuracy 99.06 # 1
Image Classification FEMNIST pFedBreD_ns_mg Accuracy 70.34 # 1
Image Classification MNIST pFedBreD_ns_mg Accuracy 92.47 # 33
Classification Sentiment140 pFedBreD_ns_mg Accuracy 73.81 # 1

Methods


No methods listed for this paper. Add relevant methods here