{"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-learning-you-may-communicate-less","title":"Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!","arxiv_id":"2306.05862","date":"2023-06-09","proceeding":null,"authors":["Milad Sefidgaran","Romain Chor","Abdellatif Zaidi","Yijun Wan"],"abstract":"We investigate the generalization error of statistical learning models in a Federated Learning (FL) setting. Specifically, we study the evolution of the generalization error with the number of communication rounds $R$ between $K$ clients and a parameter server (PS), i.e., the effect on the generalization error of how often the clients' local models are aggregated at PS. In our setup, the more the clients communicate with PS the less data they use for local training in each round, such that the amount of training data per client is identical for distinct values of $R$. We establish PAC-Bayes and rate-distortion theoretic bounds on the generalization error that account explicitly for the effect of the number of rounds $R$, in addition to the number of participating devices $K$ and individual datasets size $n$. The bounds, which apply to a large class of loss functions and learning algorithms, appear to be the first of their kind for the FL setting. Furthermore, we apply our bounds to FL-type Support Vector Machines (FSVM); and derive (more) explicit bounds in this case. In particular, we show that the generalization bound of FSVM increases with $R$, suggesting that more frequent communication with PS diminishes the generalization power. This implies that the population risk decreases less fast with $R$ than does the empirical risk. Moreover, our bound suggests that the generalization error of FSVM decreases faster than that of centralized learning by a factor of $\\mathcal{O}(\\sqrt{\\log(K)/K})$. Finally, we provide experimental results obtained using neural networks (ResNet-56) which show evidence that not only may our observations for FSVM hold more generally but also that the population risk may even start to increase beyond some value of $R$.","url_abs":"https://arxiv.org/abs/2306.05862v2","url_pdf":"https://arxiv.org/pdf/2306.05862v2.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-learning-you-may-communicate-less","repo_url":"https://github.com/romainchor/generalization_fl_icml2024","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.05862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05862"}},"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/romainchor/generalization_fl_icml2024","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"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":"cfe82136874645f0","entry":"get_flat_tensor_from_tensor_sequence","repo":"romainchor/generalization_fl_icml2024","repo_kind":"official","path":"Additional/distributed_utils.py","file_url":"https://github.com/romainchor/generalization_fl_icml2024/blob/HEAD/Additional/distributed_utils.py","link_basis":"plan_row","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":"cfe82136874645f0"}},{"code_sha256_prefix":"faa36bfafa971e5b","entry":"get_mean_flat_tensor_from_tensor_sequences","repo":"romainchor/generalization_fl_icml2024","repo_kind":"official","path":"Additional/distributed_utils.py","file_url":"https://github.com/romainchor/generalization_fl_icml2024/blob/HEAD/Additional/distributed_utils.py","link_basis":"plan_row","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":"faa36bfafa971e5b"}},{"code_sha256_prefix":"51f0988f9a7fc23d","entry":"count_correct","repo":"romainchor/generalization_fl_icml2024","repo_kind":"official","path":"Additional/train_utils.py","file_url":"https://github.com/romainchor/generalization_fl_icml2024/blob/HEAD/Additional/train_utils.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":"51f0988f9a7fc23d"}},{"code_sha256_prefix":"5a0a274086a8c169","entry":"group_weight","repo":"romainchor/generalization_fl_icml2024","repo_kind":"official","path":"Additional/train_utils.py","file_url":"https://github.com/romainchor/generalization_fl_icml2024/blob/HEAD/Additional/train_utils.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":"5a0a274086a8c169"}},{"code_sha256_prefix":"1c3ea89e818e1fa2","entry":"mkdir","repo":"romainchor/generalization_fl_icml2024","repo_kind":"official","path":"Additional/train_utils.py","file_url":"https://github.com/romainchor/generalization_fl_icml2024/blob/HEAD/Additional/train_utils.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":"1c3ea89e818e1fa2"}},{"code_sha256_prefix":"e73752eb3a5d5a4b","entry":"reduce_value","repo":"romainchor/generalization_fl_icml2024","repo_kind":"official","path":"Additional/distributed_utils.py","file_url":"https://github.com/romainchor/generalization_fl_icml2024/blob/HEAD/Additional/distributed_utils.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":"e73752eb3a5d5a4b"}},{"code_sha256_prefix":"a699c8c372b47827","entry":"resnet56_gn_swish","repo":"romainchor/generalization_fl_icml2024","repo_kind":"official","path":"Additional/models/tmp.py","file_url":"https://github.com/romainchor/generalization_fl_icml2024/blob/HEAD/Additional/models/tmp.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":"a699c8c372b47827"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}