{"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/federated-full-parameter-tuning-of-billion","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","arxiv_id":"2312.06353","date":"2023-12-11","proceeding":null,"authors":["Zhen Qin","Daoyuan Chen","Bingchen Qian","Bolin Ding","Yaliang Li","Shuiguang Deng"],"abstract":"Pre-trained large language models (LLMs) need fine-tuning to improve their responsiveness to natural language instructions. Federated learning offers a way to fine-tune LLMs using the abundant data on end devices without compromising data privacy. Most existing federated fine-tuning methods for LLMs rely on parameter-efficient fine-tuning techniques, which may not reach the performance height possible with full-parameter tuning. However, federated full-parameter tuning of LLMs is a non-trivial problem due to the immense communication cost. This work introduces FedKSeed that employs zeroth-order optimization with a finite set of random seeds. It significantly reduces transmission requirements between the server and clients to just a few random seeds and scalar gradients, amounting to only a few thousand bytes, making federated full-parameter tuning of billion-sized LLMs possible on devices. Building on it, we develop a strategy enabling probability-differentiated seed sampling, prioritizing perturbations with greater impact on model accuracy. Experiments across six scenarios with various LLMs, datasets and data partitions demonstrate that our approach outperforms existing federated LLM fine-tuning methods in both communication efficiency and new task generalization.","url_abs":"https://arxiv.org/abs/2312.06353v5","url_pdf":"https://arxiv.org/pdf/2312.06353v5.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":"federated-full-parameter-tuning-of-billion","repo_url":"https://github.com/alibaba/federatedscope","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"federated-full-parameter-tuning-of-billion","repo_url":"https://github.com/zhenqincn/fedkseed","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06353"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/zhenqincn/fedkseed","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/federatedscope","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1},"by_repo_kind":{"named_in_paper":{"samples":1,"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":0,"samples":[{"code_sha256_prefix":"c79f155710ffbb2e","entry":"MeZOFramework","repo":"zhenqincn/fedkseed","repo_kind":"named_in_paper","path":"optimizers/mezo_optimizer.py","file_url":"https://github.com/zhenqincn/fedkseed/blob/HEAD/optimizers/mezo_optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c79f155710ffbb2e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}