Papers › Personalized Federated Learning with Hidden Information on Personalized Prior

Personalized Federated Learning with Hidden Information on Personalized Prior

19 Nov 2022arXiv:2211.10684archive 2025-07-28

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.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Classification Federated Learning Image Classification Personalized Federated Learning Privacy Preserving

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Classification	Sentiment140	pFedBreD_ns_mg	Accuracy	73.81	#1 of 1	Archive leaderboard	report
Image Classification	CIFAR-10	pFedBreD_ns_mg	Percentage correct	80.63	#247 of 265	Archive leaderboard	report
Image Classification	FEMNIST	pFedBreD_ns_mg	Accuracy	70.34	#1 of 1	Archive leaderboard	report
Image Classification	Fashion-MNIST	pFedBreD_ns_mg	Accuracy	99.06	#24 of 34	Archive leaderboard	report
Image Classification	MNIST	pFedBreD_ns_mg	Accuracy	92.47	#80 of 81	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections