{"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-representation-learning-in-the","title":"Federated Representation Learning in the Under-Parameterized Regime","arxiv_id":"2406.04596","date":"2024-06-07","proceeding":null,"authors":["Renpu Liu","Cong Shen","Jing Yang"],"abstract":"Federated representation learning (FRL) is a popular personalized federated learning (FL) framework where clients work together to train a common representation while retaining their personalized heads. Existing studies, however, largely focus on the over-parameterized regime. In this paper, we make the initial efforts to investigate FRL in the under-parameterized regime, where the FL model is insufficient to express the variations in all ground-truth models. We propose a novel FRL algorithm FLUTE, and theoretically characterize its sample complexity and convergence rate for linear models in the under-parameterized regime. To the best of our knowledge, this is the first FRL algorithm with provable performance guarantees in this regime. FLUTE features a data-independent random initialization and a carefully designed objective function that aids the distillation of subspace spanned by the global optimal representation from the misaligned local representations. On the technical side, we bridge low-rank matrix approximation techniques with the FL analysis, which may be of broad interest. We also extend FLUTE beyond linear representations. Experimental results demonstrate that FLUTE outperforms state-of-the-art FRL solutions in both synthetic and real-world tasks.","url_abs":"https://arxiv.org/abs/2406.04596v4","url_pdf":"https://arxiv.org/pdf/2406.04596v4.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-representation-learning-in-the","repo_url":"https://github.com/RenpuLiu/flute","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"federated-representation-learning-in-the","repo_url":"https://github.com/KarhouTam/FL-bench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"personalized-federated-learning","task_name":"Personalized Federated Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04596"}},"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/KarhouTam/FL-bench","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RenpuLiu/flute","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":0,"samples":[{"code_sha256_prefix":"c6d3bab23c40891a","entry":"balanced_softmax_loss","repo":"RenpuLiu/flute","repo_kind":"official","path":"models/bsml.py","file_url":"https://github.com/RenpuLiu/flute/blob/HEAD/models/bsml.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6d3bab23c40891a"}},{"code_sha256_prefix":"9dc354a7407a75b8","entry":"balanced_softmax_loss","repo":"RenpuLiu/flute","repo_kind":"official","path":"utils/bsml.py","file_url":"https://github.com/RenpuLiu/flute/blob/HEAD/utils/bsml.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9dc354a7407a75b8"}},{"code_sha256_prefix":"b30a377cff8dd790","entry":"create_loss","repo":"RenpuLiu/flute","repo_kind":"official","path":"utils/bsml.py","file_url":"https://github.com/RenpuLiu/flute/blob/HEAD/utils/bsml.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b30a377cff8dd790"}},{"code_sha256_prefix":"1cc29ca74b9238bb","entry":"create_loss","repo":"RenpuLiu/flute","repo_kind":"official","path":"models/bsml.py","file_url":"https://github.com/RenpuLiu/flute/blob/HEAD/models/bsml.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1cc29ca74b9238bb"}},{"code_sha256_prefix":"b42711feaf8c8817","entry":"fun_reg_2","repo":"RenpuLiu/flute","repo_kind":"official","path":"models/Update.py","file_url":"https://github.com/RenpuLiu/flute/blob/HEAD/models/Update.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b42711feaf8c8817"}},{"code_sha256_prefix":"113b54f5013bd868","entry":"read_data","repo":"RenpuLiu/flute","repo_kind":"official","path":"utils/train_utils.py","file_url":"https://github.com/RenpuLiu/flute/blob/HEAD/utils/train_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"113b54f5013bd868"}},{"code_sha256_prefix":"49fb46a01662d68d","entry":"fun_reg","repo":"RenpuLiu/flute","repo_kind":"official","path":"models/Update.py","file_url":"https://github.com/RenpuLiu/flute/blob/HEAD/models/Update.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49fb46a01662d68d"}},{"code_sha256_prefix":"eacc168e830bc4ec","entry":"noniid","repo":"RenpuLiu/flute","repo_kind":"official","path":"utils/sampling.py","file_url":"https://github.com/RenpuLiu/flute/blob/HEAD/utils/sampling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eacc168e830bc4ec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}