{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T09:11:56Z","timestamp":1778749916412,"version":"3.51.4"},"reference-count":133,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M781597"],"award-info":[{"award-number":["2025M781597"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["XJ2026000901"],"award-info":[{"award-number":["XJ2026000901"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Federated learning (FL) has emerged as an impactful paradigm for privacy\u2010preserving machine learning, and allows model training without the need to share raw data. However, data heterogeneity across clients challenges practical FL deployment. Data space heterogeneity and statistical heterogeneity create significant training difficulties. System heterogeneity imposes additional external constraints. These combined factors impair convergence and reduce model performance. They also raise concerns regarding fairness, scalability and robustness. Focused on data heterogeneity, this review provides a structured analysis of FL. It encompasses three key areas: core categorizations of data heterogeneity, algorithmic advances (e.g., personalized FL, mixture\u2010of\u2010experts architectures, transfer learning\u2010based solutions) and system\u2010level techniques spanning communication optimization, resource adaptation and secure collaboration. We further synthesize benchmark efforts and real\u2010world applications in healthcare, finance, nuclear power and the Internet of Things (IoT)\/edge computing to highlight the practical implications of heterogeneity\u2010aware FL. Finally, we identify key challenges and outline promising research directions towards scalable, fair and adaptive FL systems capable of operating in complex real\u2010world settings. This survey aims to serve as a reference point and conceptual roadmap for future research in heterogeneous FL.<\/jats:p>","DOI":"10.1111\/exsy.70271","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:35:52Z","timestamp":1777509352000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Review of Federated Learning Under Data Heterogeneity"],"prefix":"10.1111","volume":"43","author":[{"given":"Wentao","family":"Yue","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering Lanzhou University  Lanzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyou","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering Lanzhou University  Lanzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyu","family":"Mao","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering Shenzhen University  Shenzhen China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9675-9016","authenticated-orcid":false,"given":"Qilei","family":"Li","sequence":"additional","affiliation":[{"name":"Laboratory for Artificial Intelligence and New Forms of Education, Faculty of Artificial Intelligence in Education Central China Normal University  Wuhan China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5051-3475","authenticated-orcid":false,"given":"David","family":"Camacho","sequence":"additional","affiliation":[{"name":"School of Computer Systems Engineering Universidad Politecnica de Madrid  Madrid Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567485"},{"key":"e_1_2_9_3_1","doi-asserted-by":"crossref","unstructured":"Agarwal V. K. A.Manjunatha A. V.Gribok et\u00a0al.2021.\u201cScalable Technologies Achieving Risk\u2010Informed Condition\u2010Based Predictive Maintenance Enhancing the Economic Performance of Operating Nuclear Power Plants.\u201dTechnical Report (Report No. INL\/EXT\u201021\u201064168\u2010Rev000) Idaho National Laboratory (INL).","DOI":"10.2172\/1894498"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2988293"},{"key":"e_1_2_9_5_1","unstructured":"Ali M. S. M. M.Ahsan L.Tasnim et\u00a0al.2024.\u201cFederated Learning in Healthcare: Model Misconducts Security Challenges Applications and Future Research Directions\u2013A Systematic Review.\u201darXiv Preprint arXiv:2405.13832."},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/jrfm18040179"},{"key":"e_1_2_9_7_1","first-page":"1","volume-title":"IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)","author":"Anagnostopoulos C.","year":"2024"},{"key":"e_1_2_9_8_1","first-page":"1945","volume-title":"International Conference on Machine Learning (ICML)","author":"Bietti A.","year":"2022"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3258485"},{"key":"e_1_2_9_10_1","unstructured":"Caldas S. S. M. K.Duddu P.Wu et\u00a0al.2018.\u201cLeaf: A Benchmark for Federated Settings.\u201darXiv Preprint arXiv:1812.01097."},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1504\/IJITCA.2022.124372"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673132"},{"key":"e_1_2_9_13_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen H. Y.","year":"2022"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2023.3247433"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3310097"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378161"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2988604"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2021.3082561"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJVT.2023.3341304"},{"key":"e_1_2_9_20_1","first-page":"1128","volume-title":"2022 IEEE Global Communications Conference (GLOBECOM)","author":"Chu D.","year":"2022"},{"key":"e_1_2_9_21_1","first-page":"2089","volume-title":"International Conference on Machine Learning (ICML)","author":"Collins L.","year":"2021"},{"key":"e_1_2_9_22_1","first-page":"32","volume-title":"World Congress in Computer Science, Computer Engineering & Applied Computing (CSCE)","author":"Desai H. A.","year":"2024"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523230.3523235"},{"key":"e_1_2_9_24_1","unstructured":"Dua D. andC.Graff.2019.\u201cUCI Machine Learning Repository.\u201dUniversity of California Irvine School of Information and Computer Sciences."},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0016"},{"key":"e_1_2_9_26_1","first-page":"3557","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Fallah A.","year":"2020"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714561"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2021-0030"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703790.3703795"},{"key":"e_1_2_9_30_1","first-page":"114","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Gao W.","year":"2021"},{"key":"e_1_2_9_31_1","first-page":"19545","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Ghosh A.","year":"2020"},{"key":"e_1_2_9_32_1","volume-title":"What You Need to Know About California's New Data Privacy Law","author":"Ghosh D.","year":"2018"},{"key":"e_1_2_9_33_1","first-page":"2423","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Guo P.","year":"2021"},{"key":"e_1_2_9_34_1","unstructured":"Guo S. H.Wang S.Lin X.Yang andX.Geng.2025.\u201cSTHFL: Spatio\u2010Temporal Heterogeneous Federated Learning.\u201darXiv Preprint arXiv:2501.05775."},{"key":"e_1_2_9_35_1","unstructured":"He C. M.Annavaram andS.Avestimehr.2020. \u201cTowards Non\u2010I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search.\u201d arXiv preprint arXiv:2004.08546."},{"key":"e_1_2_9_36_1","unstructured":"Herr M. D. A. B. M.Graf P.Placzek et\u00a0al.2022.\u201cBringing the Algorithms to the Data\u2013Secure Distributed Medical Analytics Using the Personal Health Train (PHT\u2010meDIC).\u201darXiv Preprint arXiv:2212.03481."},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-51999-5_4"},{"key":"e_1_2_9_38_1","first-page":"4387","volume-title":"International Conference on Machine Learning (ICML)","author":"Hsieh K.","year":"2020"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3349611.3355548"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvr7fcwb"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3177222"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"e_1_2_9_43_1","first-page":"5132","volume-title":"International Conference on Machine Learning (ICML)","author":"Karimireddy S. P.","year":"2020"},{"key":"e_1_2_9_44_1","unstructured":"Kesari A. V. R. andK. R.Kesari.2025.\u201cFluid Democracy in Federated Data Aggregation.\u201darXiv Preprint arXiv:2507.02710."},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0255397"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3581939"},{"key":"e_1_2_9_47_1","unstructured":"Krizhevsky A. andG.Hinton.2009.\u201cLearning Multiple Layers of Features From Tiny Images.\u201dTechnical Report University of Toronto."},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/EDGE55608.2022.00014"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.33980"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_9_51_1","unstructured":"Lei H. S.Gong Q.Dou andF.Farnia.2025.\u201cpFedFair: Towards Optimal Group Fairness\u2010Accuracy Trade\u2010Off in Heterogeneous Federated Learning.\u201darXiv Preprint arXiv:2503.14925."},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485929"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103497"},{"key":"e_1_2_9_54_1","first-page":"10713","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Li Q.","year":"2021"},{"key":"e_1_2_9_55_1","first-page":"1484","volume-title":"International Joint Conference on Artificial Intelligence (IJCAI)","author":"Li Q.","year":"2021"},{"key":"e_1_2_9_56_1","first-page":"6357","volume-title":"International Conference on Machine Learning (ICML)","author":"Li T.","year":"2021"},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"e_1_2_9_58_1","first-page":"133","volume-title":"International Workshop on Machine Learning in Medical Imaging (MLMI)","author":"Li W.","year":"2019"},{"key":"e_1_2_9_59_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Li X.","year":"2021"},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591976"},{"key":"e_1_2_9_61_1","unstructured":"Liang P. P. T.Liu andZ.Lea.2019. \u201cThink Locally Act Globally: Federated Learning With Local and Global Representations.\u201d arXiv preprint arXiv:2001.01523."},{"key":"e_1_2_9_62_1","volume-title":"BenchCouncil International Federated Intelligent Computing and Block Chain Conferences","author":"Liang Y.","year":"2020"},{"key":"e_1_2_9_63_1","first-page":"196","volume-title":"International Workshop on Machine Learning in Medical Imaging (MLMI)","author":"Lin L.","year":"2023"},{"issue":"226","key":"e_1_2_9_64_1","first-page":"1","article-title":"Fate: An Industrial Grade Platform for Collaborative Learning With Data Protection","volume":"22","author":"Liu Y.","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.11.001"},{"key":"e_1_2_9_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3177197"},{"key":"e_1_2_9_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2959220"},{"key":"e_1_2_9_68_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34129"},{"key":"e_1_2_9_69_1","unstructured":"Matsuda K. Y.Sasaki C.Xiao andM.Onizuka.2022.\u201cAn Empirical Study of Personalized Federated Learning.\u201darXiv Preprint arXiv:2206.13190."},{"key":"e_1_2_9_70_1","first-page":"1273","volume-title":"Artificial Intelligence and Statistics (AISTATS)","author":"McMahan B.","year":"2017"},{"key":"e_1_2_9_71_1","first-page":"127834","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Morafah M.","year":"2024"},{"key":"e_1_2_9_72_1","unstructured":"Nguyen H. T. H. V.Poor andM.Chiang.2022.\u201cContextual Model Aggregation for Fast and Robust Federated Learning in Edge Computing.\u201darXiv Preprint arXiv:2203.12738."},{"key":"e_1_2_9_73_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Nguyen J.","year":"2023"},{"key":"e_1_2_9_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-025-06989-y"},{"key":"e_1_2_9_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3385440"},{"key":"e_1_2_9_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2023.3280406"},{"key":"e_1_2_9_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596907"},{"key":"e_1_2_9_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599898"},{"key":"e_1_2_9_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC60901.2024.10612118"},{"key":"e_1_2_9_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44248-025-00079-7"},{"key":"e_1_2_9_81_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100913"},{"key":"e_1_2_9_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2846040"},{"key":"e_1_2_9_83_1","unstructured":"Ro J. H. A. T.Suresh andK.Wu.2021.\u201cFedJAX: Federated Learning Simulation With JAX.\u201darXiv preprint arXiv:2108.02117."},{"key":"e_1_2_9_84_1","unstructured":"Saadati Y. M.Rostami andM. H.Amini.2025.\u201cpMixFed: Efficient Personalized Federated Learning Through Adaptive Layer\u2010Wise Mixup.\u201darXiv Preprint arXiv:2501.11002."},{"key":"e_1_2_9_85_1","volume-title":"IEEE International Conference on Quantum Computing and Engineering (QCE)","author":"Sawaika A.","year":"2025"},{"key":"e_1_2_9_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3513221"},{"key":"e_1_2_9_87_1","first-page":"1","volume-title":"IEEE\/ACM International Conference on Computer\u2010Aided Design (ICCAD)","author":"Shafique M.","year":"2021"},{"key":"e_1_2_9_88_1","first-page":"2218","volume-title":"Proceedings of the Thirty\u2010First International Joint Conference on Artificial Intelligence (IJCAI)","author":"Shang X.","year":"2022"},{"key":"e_1_2_9_89_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-44383-9"},{"key":"e_1_2_9_90_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Sun Y.","year":"2023"},{"key":"e_1_2_9_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3338021"},{"key":"e_1_2_9_92_1","unstructured":"Tan S. andX.Liu.2024.\u201cPersonalized Federated Learning on Data With Dynamic Heterogeneity Under Limited Storage.\u201darXiv Preprint arXiv:2410.01502."},{"key":"e_1_2_9_93_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"e_1_2_9_94_1","volume-title":"Machine Learning for Healthcare Conference","author":"Tavakoli F.","year":"2024"},{"key":"e_1_2_9_95_1","volume-title":"ICLR 2019 Workshop on AI for Social Good","author":"Vepakomma P.","year":"2019"},{"key":"e_1_2_9_96_1","doi-asserted-by":"publisher","DOI":"10.2196\/35724"},{"key":"e_1_2_9_97_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3392792"},{"key":"e_1_2_9_98_1","first-page":"7611","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Wang J.","year":"2020"},{"key":"e_1_2_9_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831591"},{"key":"e_1_2_9_100_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3216326"},{"key":"e_1_2_9_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3140306"},{"key":"e_1_2_9_102_1","first-page":"1","volume-title":"International Joint Conference on Neural Networks (IJCNN)","author":"Wang Z.","year":"2024"},{"key":"e_1_2_9_103_1","unstructured":"Wang Z. F.Wu F.Yu Y.Zhou J.Hu andG.Min.2024.\u201cFederated Continual Learning for Edge\u2010Ai: A Comprehensive Survey \u201darXiv Preprint arXiv:2411.13740."},{"key":"e_1_2_9_104_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-022-01647-y"},{"key":"e_1_2_9_105_1","unstructured":"Wu C. C.Du andY.Yuan.2020.\u201cSecure Data Sharing With Flow Model.\u201darXiv Preprint arXiv:2009.11762."},{"key":"e_1_2_9_106_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3045266"},{"key":"e_1_2_9_107_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJCS.2020.2993259"},{"key":"e_1_2_9_108_1","unstructured":"Wu S. T.Li Z.Charles et\u00a0al.2022. \u201cMotley: Benchmarking Heterogeneity and Personalization in Federated Learning.\u201d arXiv preprint arXiv:2206.09262."},{"key":"e_1_2_9_109_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Wu X.","year":"2025"},{"key":"e_1_2_9_110_1","doi-asserted-by":"publisher","DOI":"10.1049\/cim2.12057"},{"key":"e_1_2_9_111_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72117-5_56"},{"key":"e_1_2_9_112_1","first-page":"20866","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xu A.","year":"2022"},{"key":"e_1_2_9_113_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3119950"},{"key":"e_1_2_9_114_1","unstructured":"Xu Y. Y.Tan C.Zhang et\u00a0al.2024.\u201cRobwe: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection.\u201darXiv Preprint arXiv:2402.19054."},{"key":"e_1_2_9_115_1","doi-asserted-by":"publisher","DOI":"10.1145\/3558005"},{"key":"e_1_2_9_116_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"e_1_2_9_117_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01139"},{"key":"e_1_2_9_118_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625558"},{"key":"e_1_2_9_119_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2026.3656194"},{"key":"e_1_2_9_120_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00151"},{"key":"e_1_2_9_121_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC52510.2021.9620852"},{"key":"e_1_2_9_122_1","doi-asserted-by":"publisher","DOI":"10.63317\/4cmohr4hcy6w"},{"key":"e_1_2_9_123_1","unstructured":"Yu S. J. P.Mu\u00f1oz andA.Jannesari.2023. \u201cResource\u2010Aware Heterogeneous Federated Learning Using Neural Architecture Search.\u201d arXiv preprint arXiv:2211.05716."},{"key":"e_1_2_9_124_1","unstructured":"Zeng D. Z.Wu S.Liu Y.Pan X.Tang andZ.Xu.2024.\u201cUnderstanding Generalization of Federated Learning: The Trade\u2010Off Between Model Stability and Optimization.\u201darXiv Preprint arXiv:2411.16303."},{"key":"e_1_2_9_125_1","first-page":"4782","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Zhang J.","year":"2023"},{"key":"e_1_2_9_126_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26330"},{"issue":"50","key":"e_1_2_9_127_1","first-page":"1","article-title":"Pfllib: A Beginner\u2010Friendly and Comprehensive Personalized Federated Learning Library and Benchmark","volume":"26","author":"Zhang J.","year":"2025","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_128_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3056185"},{"key":"e_1_2_9_129_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58951-6_20"},{"key":"e_1_2_9_130_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2939713"},{"key":"e_1_2_9_131_1","unstructured":"Zhou D. H.Tong L.Wang et\u00a0al.2025.\u201cRepresentation Learning to Advance Multi\u2010Institutional Studies With Electronic Health Record Data.\u201darXiv Preprint arXiv:2502.08547."},{"key":"e_1_2_9_132_1","doi-asserted-by":"crossref","unstructured":"Zhu H. R.Togo T.Ogawa andM.Haseyama.2024.\u201cWhich Client Is Reliable?: A Reliable and Personalized Prompt\u2010Based Federated Learning for Medical Image Question Answering.\u201darXiv Preprint arXiv:2410.17484.","DOI":"10.1109\/ICASSP48485.2024.10445933"},{"key":"e_1_2_9_133_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.098"},{"key":"e_1_2_9_134_1","first-page":"12878","volume-title":"38th International Conference on Machine Learning (ICML)","author":"Zhu Z.","year":"2021"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70271","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70271","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T08:29:33Z","timestamp":1778747373000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70271"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":133,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1111\/exsy.70271"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70271","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"assertion":[{"value":"2026-01-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70271"}}