AI Paper Atlas

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

Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape

Yan Sun, Li Shen, Shixiang Chen, Liang Ding, Dacheng Tao

ICML 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 7 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 global SAM perturbation with dynamic regularization (FedSMOO-style) versus dynamic regularization alone (ablation)FedAvg base with dynamic regularization · CIFAR-10 Pathological c=3test accuracy (%): +2.50 (77.63 to 80.13)Improved
Add SAM-correction (global perturbation correction) on top of dynamic regularization and SAM (ablation)FedSMOO · CIFAR-10 Pathological c=3test accuracy (%): +1.45 (80.13 to 81.58)Improved
Add dynamic regularization to FedAvg (ablation)FedAvg · CIFAR-10 Pathological c=3test accuracy (%): +3.55 (74.08 to 77.63)Improved
Full FedSMOO versus strongest baseline MoFedSAMFedSMOO · CIFAR-10 Dirichlet u=0.1test accuracy (%): +2.11 over second-bestImproved
Full FedSMOO versus MoFedSAM on CIFAR-100 Dirichlet u=0.6FedSMOO · CIFAR-100 Dirichlet u=0.6test accuracy (%): 53.92 vs 54.38 for MoFedSAMHurt
Use SAM-based global perturbation (FedSAM) instead of FedAvgFedSAM · CIFAR-10 Dirichlet u=0.1test accuracy (%): 76.86 vs 76.00 FedAvgNo clear effect
Add client-level momentum (MoFedSAM) to FedSAMFedSAM · CIFAR-10 Dirichlet u=0.1test accuracy (%): 76.86 to 78.71Improved
Use FedSMOO instead of FedAvg in communication-rounds to 74% on CIFAR-10 Pathological-3FedSMOO · CIFAR-10 Pathological-3communication rounds to 74%: 194 vs 723 rounds (3.73x)Improved

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