{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/beyond-local-sharpness-communication","title":"Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning","arxiv_id":"2412.03752","date":"2024-12-04","proceeding":"CVPR 2025 1","authors":["Debora Caldarola","Pietro Cagnasso","Barbara Caputo","Marco Ciccone"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2412.03752v2","url_pdf":"https://arxiv.org/pdf/2412.03752v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"beyond-local-sharpness-communication","repo_url":"https://github.com/pietrocagnasso/fedgloss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"beyond-local-sharpness-communication","repo_url":"https://github.com/debcaldarola/fedsam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[{"method_slug":"sam","method_name":"SAM"},{"method_slug":"sharpness-aware-minimization","method_name":"Sharpness-Aware Minimization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.03752","atlas_url":"https://app.syntology.ai/?focus=2412.03752","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}