{"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/c2a-client-customized-adaptation-for","title":"C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning","arxiv_id":"2411.00311","date":"2024-11-01","proceeding":null,"authors":["Yeachan Kim","Junho Kim","Wing-Lam Mok","Jun-Hyung Park","SangKeun Lee"],"abstract":"Despite the versatility of pre-trained language models (PLMs) across domains, their large memory footprints pose significant challenges in federated learning (FL), where the training model has to be distributed between a server and clients. One potential solution to bypass such constraints might be the use of parameter-efficient fine-tuning (PEFT) in the context of FL. However, we have observed that typical PEFT tends to severely suffer from heterogeneity among clients in FL scenarios, resulting in unstable and slow convergence. In this paper, we propose Client-Customized Adaptation (C2A), a novel hypernetwork-based FL framework that generates client-specific adapters by conditioning the client information. With the effectiveness of the hypernetworks in generating customized weights through learning to adopt the different characteristics of inputs, C2A can maximize the utility of shared model parameters while minimizing the divergence caused by client heterogeneity. To verify the efficacy of C2A, we perform extensive evaluations on FL scenarios involving heterogeneity in label and language distributions. Comprehensive evaluation results clearly support the superiority of C2A in terms of both efficiency and effectiveness in FL scenarios.","url_abs":"https://arxiv.org/abs/2411.00311v1","url_pdf":"https://arxiv.org/pdf/2411.00311v1.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":"c2a-client-customized-adaptation-for","repo_url":"https://github.com/yeachan-kr/c2a","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.00311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00311"}},"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/yeachan-kr/c2a","reach":{"status":"ok"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":6,"samples":[{"code_sha256_prefix":"20a6e7ef558941b5","entry":"get_num_classes","repo":"yeachan-kr/c2a","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yeachan-kr/c2a/blob/HEAD/utils.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":"20a6e7ef558941b5"}},{"code_sha256_prefix":"cecbc27814fb9527","entry":"get_tokenizer","repo":"yeachan-kr/c2a","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yeachan-kr/c2a/blob/HEAD/utils.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":"cecbc27814fb9527"}},{"code_sha256_prefix":"ec304d59b995c5e3","entry":"partition_multi_lang_data","repo":"yeachan-kr/c2a","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yeachan-kr/c2a/blob/HEAD/utils.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":"ec304d59b995c5e3"}},{"code_sha256_prefix":"d12f44df51b174b1","entry":"prune_linear_layer","repo":"yeachan-kr/c2a","repo_kind":"official","path":"transformer_utils.py","file_url":"https://github.com/yeachan-kr/c2a/blob/HEAD/transformer_utils.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":"d12f44df51b174b1"}},{"code_sha256_prefix":"bf5e8b4027b32cc7","entry":"softmax_backward_data","repo":"yeachan-kr/c2a","repo_kind":"official","path":"transformer_utils.py","file_url":"https://github.com/yeachan-kr/c2a/blob/HEAD/transformer_utils.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":"bf5e8b4027b32cc7"}},{"code_sha256_prefix":"5b30c0d84127ce4d","entry":"torch_int_div","repo":"yeachan-kr/c2a","repo_kind":"official","path":"transformer_utils.py","file_url":"https://github.com/yeachan-kr/c2a/blob/HEAD/transformer_utils.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":"5b30c0d84127ce4d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}