{"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-learning-of-large-language-models","title":"Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization","arxiv_id":"2310.15080","date":"2023-10-23","proceeding":null,"authors":["Tianshi Che","Ji Liu","Yang Zhou","Jiaxiang Ren","Jiwen Zhou","Victor S. Sheng","Huaiyu Dai","Dejing Dou"],"abstract":"Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. However, the training process of Large Language Models (LLMs) generally incurs the update of significant parameters, which limits the applicability of FL techniques to tackle the LLMs in real scenarios. Prompt tuning can significantly reduce the number of parameters to update, but it either incurs performance degradation or low training efficiency. The straightforward utilization of prompt tuning in the FL often raises non-trivial communication costs and dramatically degrades performance. In addition, the decentralized data is generally non-Independent and Identically Distributed (non-IID), which brings client drift problems and thus poor performance. This paper proposes a Parameter-efficient prompt Tuning approach with Adaptive Optimization, i.e., FedPepTAO, to enable efficient and effective FL of LLMs. First, an efficient partial prompt tuning approach is proposed to improve performance and efficiency simultaneously. Second, a novel adaptive optimization method is developed to address the client drift problems on both the device and server sides to enhance performance further. Extensive experiments based on 10 datasets demonstrate the superb performance (up to 60.8\\% in terms of accuracy) and efficiency (up to 97.59\\% in terms of training time) of FedPepTAO compared with 9 baseline approaches. Our code is available at https://github.com/llm-eff/FedPepTAO.","url_abs":"https://arxiv.org/abs/2310.15080v3","url_pdf":"https://arxiv.org/pdf/2310.15080v3.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-learning-of-large-language-models","repo_url":"https://github.com/llm-eff/fedpeptao","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.15080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15080"}},"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/llm-eff/fedpeptao","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/llm-eff/FedPepTAO","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":7,"samples":[{"code_sha256_prefix":"4a1d825b123f1168","entry":"aggregate","repo":"llm-eff/FedPepTAO","repo_kind":"official","path":"decoder-only-gpt2/evaluations.py","file_url":"https://github.com/llm-eff/FedPepTAO/blob/HEAD/decoder-only-gpt2/evaluations.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4a1d825b123f1168"}},{"code_sha256_prefix":"c2cc1135a2834ad9","entry":"get_metric_key","repo":"llm-eff/FedPepTAO","repo_kind":"official","path":"decoder-only-gpt2/run_getscore.py","file_url":"https://github.com/llm-eff/FedPepTAO/blob/HEAD/decoder-only-gpt2/run_getscore.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c2cc1135a2834ad9"}},{"code_sha256_prefix":"7be8a74b204560ff","entry":"get_metric_key","repo":"llm-eff/FedPepTAO","repo_kind":"official","path":"encoder-only-roberta-large/run_getscore.py","file_url":"https://github.com/llm-eff/FedPepTAO/blob/HEAD/encoder-only-roberta-large/run_getscore.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7be8a74b204560ff"}},{"code_sha256_prefix":"36a2201392c92c66","entry":"read_from_json","repo":"llm-eff/FedPepTAO","repo_kind":"official","path":"decoder-only-gpt2/arguments.py","file_url":"https://github.com/llm-eff/FedPepTAO/blob/HEAD/decoder-only-gpt2/arguments.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"36a2201392c92c66"}},{"code_sha256_prefix":"7b1aa9397d2f3a55","entry":"get_score","repo":"llm-eff/FedPepTAO","repo_kind":"official","path":"decoder-only-gpt2/get_score.py","file_url":"https://github.com/llm-eff/FedPepTAO/blob/HEAD/decoder-only-gpt2/get_score.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":"7b1aa9397d2f3a55"}},{"code_sha256_prefix":"48cf69dafa7e622e","entry":"get_score","repo":"llm-eff/FedPepTAO","repo_kind":"official","path":"decoder-only-llama/get_score.py","file_url":"https://github.com/llm-eff/FedPepTAO/blob/HEAD/decoder-only-llama/get_score.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":"48cf69dafa7e622e"}},{"code_sha256_prefix":"822768feef873f11","entry":"get_score","repo":"llm-eff/FedPepTAO","repo_kind":"official","path":"encoder-only-roberta-large/get_score.py","file_url":"https://github.com/llm-eff/FedPepTAO/blob/HEAD/encoder-only-roberta-large/get_score.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":"822768feef873f11"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}