{"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/fed-sb-a-silver-bullet-for-extreme","title":"Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning","arxiv_id":"2502.15436","date":"2025-02-21","proceeding":null,"authors":["Raghav Singhal","Kaustubh Ponkshe","Rohit Vartak","Lav R. Varshney","Praneeth Vepakomma"],"abstract":"Low-Rank Adaptation (LoRA) has become ubiquitous for efficiently fine-tuning foundation models. However, federated fine-tuning using LoRA is challenging due to suboptimal updates arising from traditional federated averaging of individual adapters. Existing solutions either incur prohibitively high communication cost that scales linearly with the number of clients or suffer from performance degradation due to limited expressivity. We introduce Federated Silver Bullet (Fed-SB), a novel approach for federated fine-tuning of LLMs using LoRA-SB, a recently proposed low-rank adaptation method. LoRA-SB optimally aligns the optimization trajectory with the ideal low-rank full fine-tuning projection by learning a small square matrix (R) between adapters B and A, keeping other components fixed. Direct averaging of R guarantees exact updates, substantially reducing communication cost, which remains independent of the number of clients, and enables scalability. Fed-SB achieves state-of-the-art performance across commonsense reasoning, arithmetic reasoning, and language inference tasks while reducing communication costs by up to 230x. In private settings, Fed-SB further improves performance by (1) reducing trainable parameters, thereby lowering the noise required for differential privacy and (2) avoiding noise amplification introduced by other methods. Overall, Fed-SB establishes a new Pareto frontier in the tradeoff between communication and performance, offering an efficient and scalable solution for both private and non-private federated fine-tuning. Our code is publicly available at https://github.com/CERT-Lab/fed-sb.","url_abs":"https://arxiv.org/abs/2502.15436v1","url_pdf":"https://arxiv.org/pdf/2502.15436v1.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":"fed-sb-a-silver-bullet-for-extreme","repo_url":"https://github.com/CERT-Lab/fed-sb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fed-sb-a-silver-bullet-for-extreme","repo_url":"https://github.com/RaghavSinghal10/fedex-lora","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.15436","atlas_url":"https://app.syntology.ai/?focus=2502.15436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15436"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CERT-Lab/fed-sb","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RaghavSinghal10/fedex-lora","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"16faa36d77bc31eb","entry":"evaluate","repo":"CERT-Lab/fed-sb","repo_kind":"official","path":"fed_sb/DP/SNLI/fed_trainer.py","file_url":"https://github.com/CERT-Lab/fed-sb/blob/HEAD/fed_sb/DP/SNLI/fed_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"16faa36d77bc31eb"}},{"code_sha256_prefix":"42fa1baaddd7b892","entry":"accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"42fa1baaddd7b892"}},{"code_sha256_prefix":"3414c0d2ac75a1f0","entry":"create_run_directory","repo":"CERT-Lab/fed-sb","repo_kind":"official","path":"fed_sb/fed/ARITHMETIC/train_it_fed.py","file_url":"https://github.com/CERT-Lab/fed-sb/blob/HEAD/fed_sb/fed/ARITHMETIC/train_it_fed.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3414c0d2ac75a1f0"}},{"code_sha256_prefix":"473c27f5c7f4a9cf","entry":"create_run_directory","repo":"CERT-Lab/fed-sb","repo_kind":"official","path":"fed_sb/fed/CR/train_cr_fed.py","file_url":"https://github.com/CERT-Lab/fed-sb/blob/HEAD/fed_sb/fed/CR/train_cr_fed.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"473c27f5c7f4a9cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}