AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

FedHB: Hierarchical Bayesian Federated Learning

Minyoung Kim, Timothy Hospedales

JMLR 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 11 citations (OpenAlex)

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 changedWhereMeasuredEffect
model client-wise latent variables with a hierarchical Bayesian model (NIW) instead of FedAvg-style shared parameterFedAvg · CIFAR-100 global prediction (s=100,f=0.1,tau=1)test accuracy (%): 40.87 -> 49.76Improved
hierarchical Bayesian modelling (NIW) instead of pFedBayes shared thetapFedBayes · CIFAR-100 global prediction (s=100,f=0.1,tau=1)test accuracy (%): 37.23 -> 49.76Improved
use FedHB Mixture (K=2) instead of Fed-BABUFed-BABU · CIFAR-100 personalisation (s=100,f=0.1,tau=1)test accuracy (%): 50.43 -> 56.17Improved
use FedHB NIW instead of Fed-BABUFed-BABU · CIFAR-100 personalisation (s=10,f=1.0,tau=1)test accuracy (%): 78.92 -> 82.71Improved
use FedHB NIW instead of Fed-BABUFed-BABU · CIFAR-100 global prediction (s=100,f=0.1,tau=10)test accuracy (%): 27.93 -> 29.02Improved
use FedHB Mixture (K=2) instead of Fed-BABUFed-BABU · CIFAR-C-100 personalisation, held-out corruptions (s=100,f=0.1,tau=1)test accuracy (%): 69.93 -> 74.16Improved
use FedHB NIW instead of Fed-BABUFed-BABU · CIFAR-C-100 global prediction (s=100,f=0.1,tau=1)test accuracy (%): 79.45 -> 81.22Improved
use FedHB Mixture (K=2) instead of Fed-BABUFed-BABU · MNIST global prediction (s=5,f=0.1,tau=1)test accuracy (%): 97.16 -> 97.94Improved
use FedHB Mixture (K=2) instead of Fed-BABUFed-BABU · EMNIST personalisation (s=5,f=0.2,tau=1)test accuracy (%): 83.09 -> 88.97Improved
Bayesian personalisation training after global trainingFedHB · CIFAR-100 (s=100,f=0.1,tau=10)test accuracy (%): about 4%Improved
increase number of participating clients (ablation)FedHB · MNIST trainingconvergence rateImproved
use FedHB NIW instead of Fed-BABUFed-BABU · CIFAR-100 global prediction (s=10,f=1.0,tau=10)test accuracy (%): 21.92 -> 22.87Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy