AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

FedAlign: Differentially Private Distribution Alignment for Non-IID Federated Learning

Peng Wu, Jiapeng Zhang, Yingjie Song, Xiong Xiao, Zhuo Tang

CVPR 2026 · Federated learning and privacy › Differential privacy · approach: Differentially private federated learning

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 all global unsampled data for alignment instead of 40% (ablation)FedAlign · CIFAR-10 (CNN)test accuracy at 100 rounds: about 16% higherImproved
align mean and variance (vs ignoring alignment of higher moments) (ablation)FedAlign · CIFAR-10 (CNN)test accuracyImproved
additionally align skewness and kurtosis beyond mean and variance (ablation)FedAlign · CIFAR-10 (CNN)test accuracyImproved
use FedAlign instead of FedRDNFedAlign · CIFAR-10 (β=0.05)test accuracy: 52.8 -> 54.9Improved
use FedAlign instead of FedAvgFedAlign · CIFAR-10 (β=0.1)test accuracy: 50.7 -> 54.3Improved
use FedAlign instead of Scaffold on MNISTFedAlign · MNIST (β=0.1)test accuracy: 99.12 -> 99.12No clear effect
use FedAlign instead of FedAvg on MNISTFedAlign · MNIST (β=0.05)test accuracy: 99.13 -> 99.26No clear effect

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