{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:47:42Z","timestamp":1784134062530,"version":"3.55.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:00:00Z","timestamp":1742601600000},"content-version":"vor","delay-in-days":80,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,19]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Federated learning is an upcoming machine learning paradigm which allows data from multiple sources to be used for training of classifiers without the data leaving the source it originally resides. This can be highly valuable for use cases such as medical research, where gathering data at a central location can be quite complicated due to privacy and legal concerns of the data. In such cases, federated learning has the potential to vastly speed up the research cycle. Although federated and central learning have been compared from a theoretical perspective, an extensive experimental comparison of performances and learning behavior still lacks. We have performed a comprehensive experimental comparison between federated and centralized learning. We evaluated various classifiers on various datasets exploring influences of different sample distributions as well as different class distributions across the clients. The results show similar performances under a wide variety of settings between the federated and central learning strategies. Federated learning is able to deal with various imbalances in the data distributions. It is sensitive to batch effects between different datasets when they coincide with location, similar to central learning, but this setting might go unobserved more easily. Federated learning seems to be robust to various challenges such as skewed data distributions, high data dimensionality, multiclass problems, and complex models. Taken together, the insights from our comparison gives much promise for applying federated learning as an alternative to sharing data. Code for reproducing the results in this work can be found at: https:\/\/github.com\/swiergarst\/FLComparison<\/jats:p>","DOI":"10.1093\/database\/baaf016","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T15:22:50Z","timestamp":1739892170000},"source":"Crossref","is-referenced-by-count":13,"title":["A comprehensive experimental comparison between federated and centralized learning"],"prefix":"10.1093","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4774-0309","authenticated-orcid":false,"given":"Swier","family":"Garst","sequence":"first","affiliation":[{"name":"Intelligent Systems, Delft University of Technology , van Mourik Broekmanweg 6, Delft, Zuid-Holland 2628 XE,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Dekker","sequence":"additional","affiliation":[{"name":"Intelligent Systems, Delft University of Technology , van Mourik Broekmanweg 6, Delft, Zuid-Holland 2628 XE,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcel","family":"Reinders","sequence":"additional","affiliation":[{"name":"Intelligent Systems, Delft University of Technology , van Mourik Broekmanweg 6, Delft, Zuid-Holland 2628 XE,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,3,19]]},"reference":[{"key":"2025092510530752600_R1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41666-020-00082-4","article-title":"Federated learning for healthcare informatics","volume":"5","author":"Xu","year":"2021","journal-title":"J Healthc Inform Res"},{"key":"2025092510530752600_R2","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/j.radonc.2016.10.002","article-title":"Distributed learning: developing a predictive model based on data from multiple hospitals without data leaving the hospital \u2013 a real life proof of concept","volume":"121","author":"Jochems","year":"2016","journal-title":"Radiother Oncol"},{"key":"2025092510530752600_R3","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"2025092510530752600_R4","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/TAC.2008.2009515","article-title":"Distributed subgradient methods for multi-agent optimization","volume":"54","author":"Nedic","year":"2009","journal-title":"IEEE Trans Autom Control"},{"key":"2025092510530752600_R5","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.arcontrol.2019.05.006","article-title":"A survey of distributed optimization","volume":"47","author":"Yang","year":"2019","journal-title":"Annu Rev Control"},{"key":"2025092510530752600_R6","first-page":"3347","article-title":"A survey on federated learning systems: vision, hype and reality for data privacy and protection","volume":"35","author":"Li","year":"2019","journal-title":"CoRR"},{"key":"2025092510530752600_R7","first-page":"50","article-title":"Federated learning: challenges, methods, and future directions","volume":"37","author":"Li","year":"2020","journal-title":"IEEE Signal Process Mag"},{"key":"2025092510530752600_R8","article-title":"Federated learning: strategies for improving communication efficiency","volume-title":"CoRR","author":"Konecy","year":"2016"},{"key":"2025092510530752600_R9","article-title":"Communication-efficient on-device machine learning: federated distillation and augmentation under non-IID private data","author":"Jeong","year":"2018","journal-title":"CoRR"},{"key":"2025092510530752600_R10","first-page":"4519","article-title":"Tighter theory for local SGD on identical and heterogeneous data","volume-title":"Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics","author":"Khaled","year":"2020"},{"key":"2025092510530752600_R11","article-title":"On the convergence of local descent methods in federated learning","volume-title":"CoRR","author":"Haddadpour","year":"2019"},{"key":"2025092510530752600_R12","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Karimireddy","year":"2020"},{"key":"2025092510530752600_R13","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018"},{"key":"2025092510530752600_R14","first-page":"429","article-title":"On the convergence of federated optimization in heterogeneous networks","author":"Li"},{"key":"2025092510530752600_R15","first-page":"16937","article-title":"Inverting gradients \u2013 how easy is it to break privacy in federated learning?","author":"Geiping"},{"key":"2025092510530752600_R16","first-page":"3","article-title":"Membership inference attacks against machine learning models","author":"Shokri","year":"2016"},{"key":"2025092510530752600_R17","doi-asserted-by":"crossref","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","article-title":"Federated learning with differential privacy: algorithms and performance analysis","volume":"15","author":"Wei","year":"2020","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"2025092510530752600_R18","doi-asserted-by":"publisher","DOI":"10.1093\/database\/baac112","article-title":"Coronavirus immunotherapeutic consortium database","volume":"2023","author":"Mahita","year":"2023","journal-title":"Database"},{"key":"2025092510530752600_R19","doi-asserted-by":"publisher","DOI":"10.1093\/database\/baad002","article-title":"SalivaDB\u2014a comprehensive database for salivary biomarkers in humans","volume":"2023","author":"Arora","year":"2023","journal-title":"Database"},{"key":"2025092510530752600_R20","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-022-07186-4","article-title":"Federated learning for multi-center imaging diagnostics: a simulation study in cardiovascular disease","volume":"12","author":"Linardos","year":"2022","journal-title":"Sci Rep"},{"key":"2025092510530752600_R21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0252573","article-title":"COVID-19 detection using federated machine learning","volume":"16","author":"Abdul Salam","year":"2021","journal-title":"PLoS ONE"},{"key":"2025092510530752600_R22","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc IEEE"},{"key":"2025092510530752600_R23","article-title":"Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms","volume-title":"CoRR","author":"Xiao","year":"2017"},{"key":"2025092510530752600_R24","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2019.100780","article-title":"Scalable prediction of acute myeloid leukemia using high-dimensional machine learning and blood transcriptomics","volume":"23","author":"Warnat-Herresthal","year":"2020","journal-title":"Iscience"},{"key":"2025092510530752600_R25","first-page":"6453","article-title":"Federated principal component analysis","volume":"33","author":"Andreas","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025092510530752600_R26","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1021\/acs.jmedchem.6b01611","article-title":"Profiling prediction of kinase inhibitors: toward the virtual assay","volume":"60","author":"Merget","year":"2017","journal-title":"J Med Chem"},{"key":"2025092510530752600_R27","doi-asserted-by":"crossref","first-page":"3543","DOI":"10.1109\/TMI.2021.3090082","article-title":"Multi-centre, multi-vendor and multi-disease cardiac segmentation: the M&Ms challenge","volume":"40","author":"Campello","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"2025092510530752600_R28","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1038\/s41586-021-03583-3","article-title":"Swarm learning for decentralized and confidential clinical machine learning","volume":"594","author":"Warnat-Herrestal","year":"2021","journal-title":"Nature"},{"key":"2025092510530752600_R29","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","volume-title":"CoRR","author":"Hinton","year":"2012"},{"key":"2025092510530752600_R30","first-page":"2087","article-title":"InPrivate digging: enabling tree-based distributed data mining with differential privacy","author":"Zhao","year":"2018"},{"key":"2025092510530752600_R31","doi-asserted-by":"crossref","first-page":"2463","DOI":"10.1056\/NEJMra042342","article-title":"Microarray analysis and tumor classification","volume":"354","author":"Quackenbush","year":"2006","journal-title":"N Engl J Med"},{"key":"2025092510530752600_R32","article-title":"RNA-Seq: basics, applications and protocol","author":"Mackenzie Ruairi","year":"2017"},{"key":"2025092510530752600_R33","first-page":"870","article-title":"VANTAGE6: an open source priVAcy preserviNg federaTed leArninG infrastructurE for Secure Insight eXchange","author":"Moncada-Torres","year":"2020"},{"key":"2025092510530752600_R34","article-title":"Vantage 6 repository","author":"Frank"}],"container-title":["Database"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/baaf016\/62521869\/baaf016.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/baaf016\/62521869\/baaf016.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T14:53:15Z","timestamp":1758811995000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/database\/article\/doi\/10.1093\/database\/baaf016\/8090114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1093\/database\/baaf016","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.07.26.550615","asserted-by":"object"}]},"ISSN":["1758-0463"],"issn-type":[{"value":"1758-0463","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]},"article-number":"baaf016"}}