{"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/fedpft-federated-proxy-fine-tuning-of","title":"FedPFT: Federated Proxy Fine-Tuning of Foundation Models","arxiv_id":"2404.11536","date":"2024-04-17","proceeding":null,"authors":["Zhaopeng Peng","Xiaoliang Fan","Yufan Chen","Zheng Wang","Shirui Pan","Chenglu Wen","Ruisheng Zhang","Cheng Wang"],"abstract":"Adapting Foundation Models (FMs) for downstream tasks through Federated Learning (FL) emerges a promising strategy for protecting data privacy and valuable FMs. Existing methods fine-tune FM by allocating sub-FM to clients in FL, however, leading to suboptimal performance due to insufficient tuning and inevitable error accumulations of gradients. In this paper, we propose Federated Proxy Fine-Tuning (FedPFT), a novel method enhancing FMs adaptation in downstream tasks through FL by two key modules. First, the sub-FM construction module employs a layer-wise compression approach, facilitating comprehensive FM fine-tuning across all layers by emphasizing those crucial neurons. Second, the sub-FM alignment module conducts a two-step distillations-layer-level and neuron-level-before and during FL fine-tuning respectively, to reduce error of gradient by accurately aligning sub-FM with FM under theoretical guarantees. Experimental results on seven commonly used datasets (i.e., four text and three vision) demonstrate the superiority of FedPFT.","url_abs":"https://arxiv.org/abs/2404.11536v2","url_pdf":"https://arxiv.org/pdf/2404.11536v2.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":"fedpft-federated-proxy-fine-tuning-of","repo_url":"https://github.com/pzp-dzd/fedpft","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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.11536","atlas_url":"https://app.syntology.ai/?focus=2404.11536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11536"}},"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/pzp-dzd/fedpft","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/pzpdzd/FedPFT","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"5196028f51536dcf","entry":"feed_forward_chunk","repo":"pzp-dzd/fedpft","repo_kind":"official","path":"federated_proxy_finetuning/fedparty.py","file_url":"https://github.com/pzp-dzd/fedpft/blob/HEAD/federated_proxy_finetuning/fedparty.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":"5196028f51536dcf"}},{"code_sha256_prefix":"302b4186297c9724","entry":"forward","repo":"pzp-dzd/fedpft","repo_kind":"official","path":"federated_proxy_finetuning/fedparty_cv.py","file_url":"https://github.com/pzp-dzd/fedpft/blob/HEAD/federated_proxy_finetuning/fedparty_cv.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":"302b4186297c9724"}},{"code_sha256_prefix":"76a78d956291b265","entry":"split_dataset","repo":"pzp-dzd/fedpft","repo_kind":"official","path":"federated_proxy_finetuning/fedtune.py","file_url":"https://github.com/pzp-dzd/fedpft/blob/HEAD/federated_proxy_finetuning/fedtune.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":"76a78d956291b265"}},{"code_sha256_prefix":"8e54c8752159d86c","entry":"split_feed_forward_chunk","repo":"pzp-dzd/fedpft","repo_kind":"official","path":"federated_proxy_finetuning/fedparty.py","file_url":"https://github.com/pzp-dzd/fedpft/blob/HEAD/federated_proxy_finetuning/fedparty.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":"8e54c8752159d86c"}},{"code_sha256_prefix":"0ce9306a34bc1810","entry":"split_forward","repo":"pzp-dzd/fedpft","repo_kind":"official","path":"federated_proxy_finetuning/fedparty_cv.py","file_url":"https://github.com/pzp-dzd/fedpft/blob/HEAD/federated_proxy_finetuning/fedparty_cv.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":"0ce9306a34bc1810"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}