{"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/an-empirical-study-of-personalized-federated","title":"An Empirical Study of Personalized Federated Learning","arxiv_id":"2206.13190","date":"2022-06-27","proceeding":null,"authors":["Koji Matsuda","Yuya Sasaki","Chuan Xiao","Makoto Onizuka"],"abstract":"Federated learning is a distributed machine learning approach in which a single server and multiple clients collaboratively build machine learning models without sharing datasets on clients. A challenging issue of federated learning is data heterogeneity (i.e., data distributions may differ across clients). To cope with this issue, numerous federated learning methods aim at personalized federated learning and build optimized models for clients. Whereas existing studies empirically evaluated their own methods, the experimental settings (e.g., comparison methods, datasets, and client setting) in these studies differ from each other, and it is unclear which personalized federate learning method achieves the best performance and how much progress can be made by using these methods instead of standard (i.e., non-personalized) federated learning. In this paper, we benchmark the performance of existing personalized federated learning through comprehensive experiments to evaluate the characteristics of each method. Our experimental study shows that (1) there are no champion methods, (2) large data heterogeneity often leads to high accurate predictions, and (3) standard federated learning methods (e.g. FedAvg) with fine-tuning often outperform personalized federated learning methods. We open our benchmark tool FedBench for researchers to conduct experimental studies with various experimental settings.","url_abs":"https://arxiv.org/abs/2206.13190v1","url_pdf":"https://arxiv.org/pdf/2206.13190v1.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":"an-empirical-study-of-personalized-federated","repo_url":"https://github.com/onizukalab/fedbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"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/2206.13190","atlas_url":"https://app.syntology.ai/?focus=2206.13190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13190"}},"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/onizukalab/fedbench","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":5},"by_repo_kind":{"official":{"samples":12,"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":0,"samples":[{"code_sha256_prefix":"944fedd1c33c8b12","entry":"line_to_indices","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/utils_sent140.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/utils_sent140.py","link_basis":"harvester_set","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":"944fedd1c33c8b12"}},{"code_sha256_prefix":"a88e5716356279d0","entry":"make_layers","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/model.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/model.py","link_basis":"harvester_set","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":"a88e5716356279d0"}},{"code_sha256_prefix":"9691ea80c30c06e8","entry":"matched_vgg11","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/model.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/model.py","link_basis":"harvester_set","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":"9691ea80c30c06e8"}},{"code_sha256_prefix":"340f2a473b8267d5","entry":"process_x","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/utils_sent140.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/utils_sent140.py","link_basis":"harvester_set","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":"340f2a473b8267d5"}},{"code_sha256_prefix":"0c81285c78db2513","entry":"process_y","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/utils_sent140.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/utils_sent140.py","link_basis":"harvester_set","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":"0c81285c78db2513"}},{"code_sha256_prefix":"113b54f5013bd868","entry":"read_data","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/sent140_dataset.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/sent140_dataset.py","link_basis":"harvester_set","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":"f7cd4a2b57319df7","entry":"vgg11_bn","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/model.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/model.py","link_basis":"harvester_set","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":"f7cd4a2b57319df7"}},{"code_sha256_prefix":"46db664ebd350aa3","entry":"get_dataset","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/cifar10_dataset.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/cifar10_dataset.py","link_basis":"harvester_set","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":"46db664ebd350aa3"}},{"code_sha256_prefix":"02e3e53196e5871e","entry":"get_dataset","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/femnist_dataset.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/femnist_dataset.py","link_basis":"harvester_set","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":"02e3e53196e5871e"}},{"code_sha256_prefix":"e34e4f12bbf9cb40","entry":"get_dataset","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/mnist_dataset.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/mnist_dataset.py","link_basis":"harvester_set","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":"e34e4f12bbf9cb40"}},{"code_sha256_prefix":"3f9fb06d152c383a","entry":"get_dataset","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/sent140_dataset.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/sent140_dataset.py","link_basis":"harvester_set","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":"3f9fb06d152c383a"}},{"code_sha256_prefix":"ad7ba8392208f3dd","entry":"get_dataset","repo":"onizukalab/fedbench","repo_kind":"official","path":"code/utils/shakespeare_dataset.py","file_url":"https://github.com/onizukalab/fedbench/blob/HEAD/code/utils/shakespeare_dataset.py","link_basis":"harvester_set","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":"ad7ba8392208f3dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}