AI Paper Atlas

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

Few-for-Many Personalized Federated Learning

Ping Guo, Tiantian Zhang, Xi Lin, Xiang Li, Zhi-Ri Tang, Qingfu Zhang

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Personalization with global-local trade-off · 0 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
use FedFew instead of FedRepFedFew · CIFAR-100 pathological M=20accuracy: 61.46 -> 64.98Improved
use FedFew instead of FedRepFedFew · CIFAR-100 pathological M=10accuracy: 66.50 -> 65.47Hurt
use FedFew instead of strongest baselineFedFew · CIFAR-100 practical M=20accuracy: 53.69% surpassing best baseline by 7.02%Improved
use FedFew instead of FedRepFedFew · TinyImageNetaccuracy: 27.24 -> 30.31 (+3.07)Improved
use FedFew instead of FedRepFedFew · AG Newsaccuracy: 94.68 -> 96.07 (+1.39)Improved
use FedFew instead of APFLFedFew · CIFAR-10 practical M=10accuracy: 88.38 -> 88.17Hurt
use FedFew instead of IFCA multi-model baselineFedFew · FedISICaverage accuracy: 53.61 -> 69.57Improved
use FedFew instead of local-only trainingFedFew · FedISIC minimum accuracymin accuracy: +13.0% over local-onlyImproved
increase number of server models K (ablation)FedFew · CIFAR-10 (Dirichlet 0.5, M=20)weighted accuracy: 89.4 to 91.3, K=1 highest at 91.3No clear effect
add multiple server models (K>1) versus single model (ablation)FedFew · CIFAR-10 (Dirichlet 0.5, M=20)weighted accuracy: 91.3 -> 89.4 to 91.3No clear effect
increase local epochs from 2 to 16 at fixed compute (ablation)FedFew · CIFAR-10 communicationmean client accuracy: 88.3 -> 87.8No clear effect
increase K, convergence of STCH-Set objective (ablation)FedFew · CIFAR-10convergence speed: convergence slows as K growsHurt

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