AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Toward the Flatter Landscape and Better Generalization in Federated Learning Under Client-Level Differential Privacy

Yifan Shi, Kang Wei, Li Shen, Yingqi Liu, Xueqian Wang, Bo Yuan, Dacheng Tao

TPAMI 2025 · Federated learning and privacy › Differential privacy · approach: Differentially private federated learning · 12 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
replace local SGD with SAM optimizerDP-FedAvg · CIFAR-10 (Dirichlet 0.6)validation accuracy (%): 50.05 -> 54.14Improved
replace local SGD with SAM optimizerDP-FedAvg · CIFAR-100 (Dirichlet 0.6)validation accuracy (%): 15.92 -> 19.09Improved
replace local SGD with SAM optimizerDP-FedAvg · EMNIST (Dirichlet 0.6)validation accuracy (%): 82.20 -> 84.32Improved
add top-k local update sparsification (p=0.4) to DP-FedSAM (ablation)DP-FedSAM · CIFAR-10 (Dirichlet 0.6)validation accuracy (%): 54.14 -> 57.00Improved
add top-k local update sparsification (p=0.4) to DP-FedSAM (ablation)DP-FedSAM · CIFAR-100 (Dirichlet 0.6)validation accuracy (%): 19.09 -> 21.24Improved
lower sparsity ratio from p=0.4 to p=0.1 (ablation)DP-FedSAM-topk · CIFAR-10 (Dirichlet 0.6)validation accuracy (%): 57.00 -> 55.05Hurt
raise sparsity ratio from p=0.4 to p=0.8 (ablation)DP-FedSAM-topk · CIFAR-100 (Dirichlet 0.6)validation accuracy (%): 21.24 -> 19.79Hurt
replace Fed-SMP-topk with DP-FedSAM-topk (SAM added) (ablation)Fed-SMP-topk · EMNIST (Dirichlet 0.6)generalization gap (train-val, %): 16.31 -> 11.07Improved
replace DP-FedAvg with DP-FedSAM (ablation)DP-FedAvg · EMNIST (Dirichlet 0.6)generalization gap (train-val, %): 17.35 -> 10.75Improved
replace DP-FedAvg with DP-FedSAM-topk under privacy budget epsilon=4DP-FedAvg · CIFAR-10 (Dirichlet 0.6)test accuracy (%): 38.23 -> 38.96Improved
replace DP-FedAvg with DP-FedSAM-topk under privacy budget epsilon=10DP-FedAvg · CIFAR-10 (Dirichlet 0.6)test accuracy (%): 49.06 -> 56.36Improved
replace DP-FedAvg with DP-FedSAM-topk under privacy budget epsilon=10DP-FedAvg · CIFAR-100 (Dirichlet 0.6)test accuracy (%): 15.23 -> 20.79Improved

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