AI Paper Atlas

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

Class-Wise Federated Averaging for Efficient Personalization

Gyuejeong Lee, Daeyoung Choi

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Sparse and collaboration-graph personalization · 6 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
add WDR regularization to cwFedAvg with approximated distribution (ablation)cwFedAvg · CIFAR-100 (practical, alpha=0.1, cwFedAvg on all layers)accuracy: 32.25 -> 54.99Improved
add WDR regularization to cwFedAvg with approximated distribution (ablation)cwFedAvg · Tiny ImageNet (practical, alpha=0.1, all layers)accuracy: 20.08 -> 38.94Improved
use approximated distribution with WDR instead of empirical distribution (ablation)cwFedAvg · CIFAR-100 (practical, alpha=0.1, cwFedAvg on all layers)accuracy: 48.27 -> 54.99Improved
use approximated distribution without WDR instead of FedAvg (ablation)cwFedAvg · CIFAR-100 (practical, alpha=0.1, cwFedAvg on all layers)accuracy: 32.44 -> 32.25No clear effect
apply cwFedAvg only to output layer instead of all layers (ablation)cwFedAvg · CIFAR-100 (practical, alpha=0.1, layer-selective)accuracy: 54.99 -> 56.29Improved
apply cwFedAvg only to output layer instead of all layers (ablation)cwFedAvg · Tiny ImageNet (practical, alpha=0.1, layer-selective)accuracy: 38.94 -> 41.38Improved
apply cwFedAvg only to output layer instead of all layers (ablation)cwFedAvg · CIFAR-100 (pathological, layer-selective)accuracy: 65.91 -> 67.50Improved
use cwFedAvg instead of FedAvg (ablation)cwFedAvg · CIFAR-100 (pathological)accuracy: 28.22 -> 67.50Improved
use cwFedAvg instead of FedAMP on CIFAR-10 practicalcwFedAvg · CIFAR-10 (practical, alpha=0.1)accuracy: 89.46 -> 88.65Hurt
increase number of clients from 50 to 100cwFedAvg · CIFAR-100 (clients)accuracy: 55.90 -> 53.54Hurt
increase alpha toward IID (1.0)cwFedAvg vs FedAvg · CIFAR-100 (alpha=1.0, 20 clients)accuracy: 37.50 vs 36.75No clear effect
use cwFedAvg instead of FedAMP at low heterogeneity alpha=0.5cwFedAvg · CIFAR-100 (alpha=0.5, 20 clients)accuracy: 25.41 -> 40.78Improved

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