{"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/the-effect-of-personalization-in-fedprox-a","title":"Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees","arxiv_id":"2410.08934","date":"2024-10-11","proceeding":null,"authors":["Xin Yu","Zelin He","Ying Sun","Lingzhou Xue","Runze Li"],"abstract":"Personalized federated learning (PFL) offers a flexible framework for aggregating information across distributed clients with heterogeneous data. This work considers a personalized federated learning setting that simultaneously learns global and local models. While purely local training has no communication cost, collaborative learning among the clients can leverage shared knowledge to improve statistical accuracy, presenting an accuracy-communication trade-off in personalized federated learning. However, the theoretical analysis of how personalization quantitatively influences sample and algorithmic efficiency and their inherent trade-off is largely unexplored. This paper makes a contribution towards filling this gap, by providing a quantitative characterization of the personalization degree on the tradeoff. The results further offers theoretical insights for choosing the personalization degree. As a side contribution, we establish the minimax optimality in terms of statistical accuracy for a widely studied PFL formulation. The theoretical result is validated on both synthetic and real-world datasets and its generalizability is verified in a non-convex setting.","url_abs":"https://arxiv.org/abs/2410.08934v4","url_pdf":"https://arxiv.org/pdf/2410.08934v4.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":"the-effect-of-personalization-in-fedprox-a","repo_url":"https://github.com/ZLHe0/fedprox-bilevel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"personalized-federated-learning","task_name":"Personalized Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.08934","atlas_url":"https://app.syntology.ai/?focus=2410.08934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08934"}},"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":"deterministic:regex_extraction","url":"https://github.com/ZLHe0/fedclup","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZLHe0/fedprox-bilevel","reach":{"status":"ok"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":8,"ran":7,"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":"07dc3f8d04ab4358","entry":"calculate_mu_and_L","repo":"ZLHe0/fedclup","repo_kind":"found_in_text","path":"src/simulation/simulation_main.py","file_url":"https://github.com/ZLHe0/fedclup/blob/HEAD/src/simulation/simulation_main.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":"07dc3f8d04ab4358"}},{"code_sha256_prefix":"fd7e09dff353236b","entry":"load_and_scale_data","repo":"ZLHe0/fedclup","repo_kind":"found_in_text","path":"src/simulation/simulation_main.py","file_url":"https://github.com/ZLHe0/fedclup/blob/HEAD/src/simulation/simulation_main.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":"fd7e09dff353236b"}},{"code_sha256_prefix":"c6e917f24ee922de","entry":"load_data","repo":"ZLHe0/fedclup","repo_kind":"found_in_text","path":"src/mnist_main.py","file_url":"https://github.com/ZLHe0/fedclup/blob/HEAD/src/mnist_main.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":"c6e917f24ee922de"}},{"code_sha256_prefix":"93418897624bb932","entry":"load_stat_results","repo":"ZLHe0/fedclup","repo_kind":"found_in_text","path":"src/simulation/visualize_stat_error.py","file_url":"https://github.com/ZLHe0/fedclup/blob/HEAD/src/simulation/visualize_stat_error.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":"93418897624bb932"}},{"code_sha256_prefix":"5a195d5207d0c061","entry":"load_total_results","repo":"ZLHe0/fedclup","repo_kind":"found_in_text","path":"src/simulation/visualize_local_epochs.py","file_url":"https://github.com/ZLHe0/fedclup/blob/HEAD/src/simulation/visualize_local_epochs.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":"5a195d5207d0c061"}},{"code_sha256_prefix":"0b4eeac7df7c70c5","entry":"load_total_results","repo":"ZLHe0/fedclup","repo_kind":"found_in_text","path":"src/simulation/visualize_total_error.py","file_url":"https://github.com/ZLHe0/fedclup/blob/HEAD/src/simulation/visualize_total_error.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":"0b4eeac7df7c70c5"}},{"code_sha256_prefix":"276ab0278e14d2f9","entry":"local_training_update","repo":"ZLHe0/fedclup","repo_kind":"found_in_text","path":"src/simulation/simulation_main.py","file_url":"https://github.com/ZLHe0/fedclup/blob/HEAD/src/simulation/simulation_main.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":"276ab0278e14d2f9"}},{"code_sha256_prefix":"13a71c5634bb7dc5","entry":"generate_device_data","repo":"ZLHe0/fedclup","repo_kind":"found_in_text","path":"src/simulation/generate_data.py","file_url":"https://github.com/ZLHe0/fedclup/blob/HEAD/src/simulation/generate_data.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":"13a71c5634bb7dc5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}