paper-with-me

홈 › Papers

FedNSAM:Consistency of Local and Global Flatness for Federated Learning

2026-02-27 · Junkang Liu, Fanhua Shang, Yuxuan Tian, Hongying Liu, Yuanyuan Liu arxiv

In federated learning (FL), multi-step local updates and data heterogeneity usually lead to sharper global minima, which degrades the performance of the global model. Popular FL algorithms integrate sharpness-aware minimization (SAM) into local training to address this issue. However, in the high data heterogeneity setting, the flatness in local training does not imply the flatness of the global model. Therefore, minimizing the sharpness of the local loss surfaces on the client data does not enable the effectiveness of SAM in FL to improve the generalization ability of the global model. We define the \textbf{flatness distance} to explain this phenomenon. By rethinking the SAM in FL and theoretically analyzing the \textbf{flatness distance}, we propose a novel \textbf{FedNSAM} algorithm that accelerates the SAM algorithm by introducing global Nesterov momentum into the local update to harmonize the consistency of global and local flatness. \textbf{FedNSAM} uses the global Nesterov momentum as the direction of local estimation of client global perturbations and extrapolation. Theoretically, we prove a tighter convergence bound than FedSAM by Nesterov extrapolation. Empirically, we conduct comprehensive experiments on CNN and Transformer models to verify the superior performance and efficiency of \textbf{FedNSAM}. The code is available at https://github.com/junkangLiu0/FedNSAM.

📄 PDF Abstract BibTeX arXiv:2602.23827

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning

2026-05-09 · Bingnan Xiao, Yuan Gao, Bingcong Li, Wei Ni 외 arxiv

Sharpness-aware minimization (SAM) is an effective method for improving the generalization of federated learning (FL) by steering local training toward flat minima. Under data heterogeneity, however, device-side SAM sear…

Federated Learning

Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning

2025-12-09 · M Yashwanth, Gaurav Kumar Nayak, Harsh Rangwani, Arya Singh 외 arxiv

Federated Learning (FL) is an emerging machine learning framework that enables multiple clients (coordinated by a server) to collaboratively train a global model by aggregating the locally trained models without sharing …

Federated Learning

DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm

2025-10-31 · Junkang Liu, Yuxuan Tian, Fanhua Shang, Yuanyuan Liu 외 arxiv

To prevent inference attacks in Federated Learning (FL) and reduce the leakage of sensitive information, Client-level Differentially Private Federated Learning (CL-DPFL) is widely used. However, current CL-DPFL methods u…

Federated Learning

Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning

2024-12-04 · CVPR 2025 1 · Debora Caldarola, Pietro Cagnasso, Barbara Caputo, Marco Ciccone

Federated learning (FL) enables collaborative model training with privacy preservation. Data heterogeneity across edge devices (clients) can cause models to converge to sharp minima, negatively impacting generalization a…

Federated Learning

Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization

2024-05-29 · Ziqing Fan, Shengchao Hu, Jiangchao Yao, Gang Niu 외

In federated learning (FL), the multi-step update and data heterogeneity among clients often lead to a loss landscape with sharper minima, degenerating the performance of the resulted global model. Prevalent federated ap…

Federated Learning