AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

FedPop: A Bayesian Approach for Personalised Federated Learning

Nikita Yurevich Kotelevskii, Maxime Vono, Alain Durmus, Eric Moulines

NeurIPS 2022 · Federated learning and privacy › Communication-efficient FL · approach: Local drift correction · 3 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
FedSOUL vs best baseline FedRepFedSOUL · CIFAR-10 (100,2)accuracy: 87.70 -> 91.12Improved
FedSOUL vs best baseline FedRepFedSOUL · CIFAR-10 (100,5)accuracy: 75.68 -> 79.48Improved
FedSOUL vs best baseline FedRepFedSOUL · CIFAR-100 (100,20)accuracy: 56.10 -> 59.73Improved
FedSOUL vs best baseline DITTOFedSOUL · CIFAR-100 (100,5)accuracy: 79.15 -> 79.56Improved
FedSOUL vs local learning onlyFedSOUL · CIFAR-10 (100,2)accuracy: 89.79 -> 91.12Improved
add fine-tuning to FedAvgFedAvg · CIFAR-10 (100,2)accuracy: 42.65 -> 85.63Improved
add fine-tuning to FedAvgFedAvg · CIFAR-100 (100,20)accuracy: 31.97 -> 56.19Improved
non-personalised SCAFFOLD vs FedAvgSCAFFOLD · CIFAR-10 (100,2)accuracy: 42.65 -> 37.72Hurt
use common prior with small synthetic datasets (FedSOUL vs FedRep/FedAvg)FedSOUL · synthetic regression, small dataprincipal angle distance and l2 normImproved
FedSOUL vs FedRep with 10%, 50%, 90% small clientsFedSOUL · CIFAR-10/100 small dataaverage accuracyImproved
run FedPop without warm-start, needing M=50 (ablation)FedSOUL · syntheticperformance: M=50No clear effect
compare FedPop with non-federated stochastic approximation, T=100FedPop · syntheticrelative l2 error: less than 10^-3Improved

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