{"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/deer-deviation-eliminating-and-noise","title":"DEeR: Deviation Eliminating and Noise Regulating for Privacy-preserving Federated Low-rank Adaptation","arxiv_id":"2410.12926","date":"2024-10-16","proceeding":null,"authors":["Meilu Zhu","Axiu Mao","Jun Liu","Yixuan Yuan"],"abstract":"Integrating low-rank adaptation (LoRA) with federated learning (FL) has received widespread attention recently, aiming to adapt pretrained foundation models (FMs) to downstream medical tasks via privacy-preserving decentralized training. However, owing to the direct combination of LoRA and FL, current methods generally undergo two problems, i.e., aggregation deviation, and differential privacy (DP) noise amplification effect. To address these problems, we propose a novel privacy-preserving federated finetuning framework called \\underline{D}eviation \\underline{E}liminating and Nois\\underline{e} \\underline{R}egulating (DEeR). Specifically, we firstly theoretically prove that the necessary condition to eliminate aggregation deviation is guaranteing the equivalence between LoRA parameters of clients. Based on the theoretical insight, a deviation eliminator is designed to utilize alternating minimization algorithm to iteratively optimize the zero-initialized and non-zero-initialized parameter matrices of LoRA, ensuring that aggregation deviation always be zeros during training. Furthermore, we also conduct an in-depth analysis of the noise amplification effect and find that this problem is mainly caused by the ``linear relationship'' between DP noise and LoRA parameters. To suppress the noise amplification effect, we propose a noise regulator that exploits two regulator factors to decouple relationship between DP and LoRA, thereby achieving robust privacy protection and excellent finetuning performance. Additionally, we perform comprehensive ablated experiments to verify the effectiveness of the deviation eliminator and noise regulator. DEeR shows better performance on public medical datasets in comparison with state-of-the-art approaches. The code is available at https://github.com/CUHK-AIM-Group/DEeR.","url_abs":"https://arxiv.org/abs/2410.12926v1","url_pdf":"https://arxiv.org/pdf/2410.12926v1.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":"deer-deviation-eliminating-and-noise","repo_url":"https://github.com/cuhk-aim-group/deer","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"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.12926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12926"}},"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/cuhk-aim-group/deer","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":8,"samples":[{"code_sha256_prefix":"2ba286d69c901126","entry":"Client_update","repo":"cuhk-aim-group/deer","repo_kind":"official","path":"client_funct.py","file_url":"https://github.com/cuhk-aim-group/deer/blob/HEAD/client_funct.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":"2ba286d69c901126"}},{"code_sha256_prefix":"747d0b39f329a800","entry":"build_non_iid_by_dirichlet","repo":"cuhk-aim-group/deer","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/cuhk-aim-group/deer/blob/HEAD/datasets.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":"747d0b39f329a800"}},{"code_sha256_prefix":"73c33606d16472c4","entry":"client_localTrain","repo":"cuhk-aim-group/deer","repo_kind":"official","path":"client_funct.py","file_url":"https://github.com/cuhk-aim-group/deer/blob/HEAD/client_funct.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":"73c33606d16472c4"}},{"code_sha256_prefix":"4e06dd2dcc293a25","entry":"receive_server_model","repo":"cuhk-aim-group/deer","repo_kind":"official","path":"client_funct.py","file_url":"https://github.com/cuhk-aim-group/deer/blob/HEAD/client_funct.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":"4e06dd2dcc293a25"}},{"code_sha256_prefix":"8737c82de631cffc","entry":"swish","repo":"cuhk-aim-group/deer","repo_kind":"official","path":"models_dict/efficientnet.py","file_url":"https://github.com/cuhk-aim-group/deer/blob/HEAD/models_dict/efficientnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8737c82de631cffc"}},{"code_sha256_prefix":"076b0d967ea9301b","entry":"DenseNet121","repo":"cuhk-aim-group/deer","repo_kind":"official","path":"models_dict/densenet.py","file_url":"https://github.com/cuhk-aim-group/deer/blob/HEAD/models_dict/densenet.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":"076b0d967ea9301b"}},{"code_sha256_prefix":"f531a4dff30d1abb","entry":"DenseNet169","repo":"cuhk-aim-group/deer","repo_kind":"official","path":"models_dict/densenet.py","file_url":"https://github.com/cuhk-aim-group/deer/blob/HEAD/models_dict/densenet.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":"f531a4dff30d1abb"}},{"code_sha256_prefix":"c7097ac9c438b6cb","entry":"DenseNet201","repo":"cuhk-aim-group/deer","repo_kind":"official","path":"models_dict/densenet.py","file_url":"https://github.com/cuhk-aim-group/deer/blob/HEAD/models_dict/densenet.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":"c7097ac9c438b6cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}