{"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/flora-federated-fine-tuning-large-language","title":"FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations","arxiv_id":"2409.05976","date":"2024-09-09","proceeding":null,"authors":["Ziyao Wang","Zheyu Shen","Yexiao He","Guoheng Sun","Hongyi Wang","Lingjuan Lyu","Ang Li"],"abstract":"The rapid development of Large Language Models (LLMs) has been pivotal in advancing AI, with pre-trained LLMs being adaptable to diverse downstream tasks through fine-tuning. Federated learning (FL) further enhances fine-tuning in a privacy-aware manner by utilizing clients' local data through in-situ computation, eliminating the need for data movement. However, fine-tuning LLMs, given their massive scale of parameters, poses challenges for clients with constrained and heterogeneous resources in FL. Previous methods employed low-rank adaptation (LoRA) for efficient federated fine-tuning but utilized traditional FL aggregation strategies on LoRA adapters. These approaches led to mathematically inaccurate aggregation noise, reducing fine-tuning effectiveness and failing to address heterogeneous LoRAs. In this work, we first highlight the mathematical incorrectness of LoRA aggregation in existing federated fine-tuning methods. We introduce a new approach called FLORA that enables federated fine-tuning on heterogeneous LoRA adapters across clients through a novel stacking-based aggregation method. Our approach is noise-free and seamlessly supports heterogeneous LoRA adapters. Extensive experiments demonstrate FLORA' s superior performance in both homogeneous and heterogeneous settings, surpassing state-of-the-art methods. We envision this work as a milestone for efficient, privacy-preserving, and accurate federated fine-tuning of LLMs. Our code is available at https://github.com/ATP-1010/FederatedLLM.","url_abs":"https://arxiv.org/abs/2409.05976v1","url_pdf":"https://arxiv.org/pdf/2409.05976v1.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":"flora-federated-fine-tuning-large-language","repo_url":"https://github.com/atp-1010/federatedllm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.05976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05976"}},"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/atp-1010/federatedllm","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":2},"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":3,"samples":[{"code_sha256_prefix":"367dbfbd1a9d509f","entry":"client_selection","repo":"atp-1010/federatedllm","repo_kind":"official","path":"fed_utils/client_participation_scheduling.py","file_url":"https://github.com/atp-1010/federatedllm/blob/HEAD/fed_utils/client_participation_scheduling.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":"367dbfbd1a9d509f"}},{"code_sha256_prefix":"516cac45490ea6a7","entry":"FedAvg","repo":"atp-1010/federatedllm","repo_kind":"official","path":"fed_utils/model_aggregation.py","file_url":"https://github.com/atp-1010/federatedllm/blob/HEAD/fed_utils/model_aggregation.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":"516cac45490ea6a7"}},{"code_sha256_prefix":"c973c27a00616d47","entry":"global_evaluation","repo":"atp-1010/federatedllm","repo_kind":"official","path":"fed_utils/evaluation.py","file_url":"https://github.com/atp-1010/federatedllm/blob/HEAD/fed_utils/evaluation.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":"c973c27a00616d47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}