Papers › Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization...

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

4 Dec 2024CVPR 2025 1arXiv:2412.03752archive 2025-07-28

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 and robustness. Recent approaches use client-side sharpness-aware minimization (SAM) to encourage flatter minima, but the discrepancy between local and global loss landscapes often undermines their effectiveness, as optimizing for local sharpness does not ensure global flatness. This work introduces FedGloSS (Federated Global Server-side Sharpness), a novel FL approach that prioritizes the optimization of global sharpness on the server, using SAM. To reduce communication overhead, FedGloSS cleverly approximates sharpness using the previous global gradient, eliminating the need for additional client communication. Our extensive evaluations demonstrate that FedGloSS consistently reaches flatter minima and better performance compared to state-of-the-art FL methods across various federated vision benchmarks.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

pietrocagnasso/fedgloss officialmentioned in papermentioned on GitHubpytorchBSD-2-Clause report
debcaldarola/fedsam mentioned on GitHubpytorchBSD-2-Clause report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Federated Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SAMSharpness-Aware Minimization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections