{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T18:44:19Z","timestamp":1768416259371,"version":"3.49.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T00:00:00Z","timestamp":1669248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.U19A2059"],"award-info":[{"award-number":["No.U19A2059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["No. 206999977"],"award-info":[{"award-number":["No. 206999977"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Federated Learning is a distributed machine learning framework that aims to train a global shared model while keeping their data locally, and previous researches have empirically proven the ideal performance of federated learning methods. However, recent researches found the challenge of statistical heterogeneity caused by the non-independent and identically distributed (non-IID), which leads to a significant decline in the performance of federated learning because of the model divergence caused by non-IID data. This statistical heterogeneity is dramatically restricts the application of federated learning and has become one of the critical challenges in federated learning. In this paper, a dynamic weighted model aggregation algorithm based on statistical heterogeneity for federated learning called DWFed is proposed, in which the index of statistical heterogeneity is firstly quantitatively defined through derivation. Then the index is used to calculate the weights of each local model for aggregating federated model, which is to constrain the model divergence caused by non-IID data. Multiple experiments on public benchmark data set reveal the improvements in performance and robustness of the federated models in heterogeneous settings.<\/jats:p>","DOI":"10.3389\/fnbot.2022.1041553","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T12:33:35Z","timestamp":1669293215000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["DWFed: A statistical- heterogeneity-based dynamic weighted model aggregation algorithm for federated learning"],"prefix":"10.3389","volume":"16","author":[{"given":"Aiguo","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingfu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guiduo","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3390\/app10082864","article-title":"Fedopt: towards communication efficiency and privacy preservation in federated learning","author":"Asad","year":"2020","journal-title":"Appl. Sci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"19","DOI":"10.3233\/HIS-220006","article-title":"Federated learning: applications, challenges and future directions","volume":"18","author":"Bharati","year":"2022","journal-title":"Int. J. Hybrid Intel.l Syst"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8951961","article-title":"Machine and deep learning for iot security and privacy: applications, challenges, and future directions","author":"Bharati","year":"2022","journal-title":"Security Commun. Netw"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.908814","article-title":"An emd-based adaptive client selection algorithm for federated learning in heterogeneous data scenarios","author":"Chen","year":"2022","journal-title":"Front. Plant Sci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e0230706","DOI":"10.1371\/journal.pone.0230706","article-title":"Loadaboost: Loss-based adaboost federated machine learning on medical data","volume":"15","author":"Huang","year":"2018","journal-title":"PLoS ONE"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1811.11479","article-title":"Communication-efficient on-device machine learning: federated distillation and augmentation under non-iid private data","author":"Jeong","year":"2018","journal-title":"arXiv preprint arXiv:1811.11479"},{"key":"B7","doi-asserted-by":"publisher","first-page":"315","DOI":"10.5555\/2999611.2999647","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume":"26","author":"Johnson","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1511.03575","article-title":"Federated optimization: distributed optimization beyond the datacenter","author":"Kone\u010dn\u1ef3","year":"2015","journal-title":"arXiv preprint arXiv:1511.03575"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1610.05492","article-title":"Federated learning: strategies for improving communication efficiency","author":"Kone\u010dn\u1ef3","year":"2016","journal-title":"arXiv [Preprint]."},{"key":"B10","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"B11","doi-asserted-by":"publisher","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":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.03581","article-title":"Fedmd: heterogenous federated learning via model distillation","author":"Li","year":"2019","journal-title":"arXiv preprint arXiv:1910.03581"},{"key":"B13","first-page":"6357","article-title":"\u201cDitto: fair and robust federated learning through personalization,\u201d","author":"Li","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.06127","article-title":"Federated optimization in heterogeneous networks","author":"Li","year":"2018","journal-title":"arXiv preprint arXiv:1812.06127"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.02189","article-title":"On the convergence of fedavg on non-iid data","author":"Li","year":"2019","journal-title":"arXiv preprint arXiv:1907.02189"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1602.05629","article-title":"Federated learning: Collaborative machine learning without centralized training data","author":"McMahan","year":"2017","journal-title":"arXiv [Preprint]."},{"key":"B17","author":"McMahan","year":"2017"},{"key":"B18","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1145\/2492348.2492354","article-title":"\u201cService-oriented heterogeneous resource sharing for optimizing service latency in mobile cloud,\u201d","volume-title":"Proceedings of the First International Workshop on Mobile Cloud Computing and Networking","author":"Nishio","year":"2013"},{"key":"B19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICC.2019.8761315","article-title":"\u201cClient selection for federated learning with heterogeneous resources in mobile edge,\u201d","volume-title":"ICC 2019-2019 IEEE International Conference on Communications (ICC)","author":"Nishio","year":"2019"},{"key":"B20","doi-asserted-by":"publisher","first-page":"3088","DOI":"10.1109\/JIOT.2020.3007662","article-title":"Realizing the heterogeneity: a self-organized federated learning framework for iot","volume":"8","author":"Pang","year":"2020","journal-title":"IEEE Internet Things J"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10586-022-03658-4","article-title":"Federated learning-based ai approaches in smart healthcare: concepts, taxonomies, challenges and open issues","volume":"17","author":"Rahman","year":"2022","journal-title":"Cluster Comput"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3143576","article-title":"IoMT: a COVID-19 healthcare system driven by federated learning and blockchain","author":"Samuel","year":"2022","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B23","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1109\/TSIPN.2015.2448520","article-title":"Joint optimization of radio and computational resources for multicell mobile-edge computing","volume":"1","author":"Sardellitti","year":"2015","journal-title":"IEEE Trans. Signal Inform. Process. Over Netw"},{"key":"B24","doi-asserted-by":"publisher","first-page":"3400","DOI":"10.1109\/TNNLS.2019.2944481","article-title":"Robust and communication-efficient federated learning from non-iid data","volume":"31","author":"Sattler","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B25","volume-title":"The Complete Works of William Shakespeare","author":"Shakespeare","year":"2007"},{"key":"B26","first-page":"1000","article-title":"\u201cCommunication-efficient distributed optimization using an approximate newton-type method,\u201d","volume-title":"International Conference on Machine Learning","author":"Shamir","year":"2014"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103627","article-title":"A review on deep learning approaches in healthcare systems: taxonomies, challenges, and open issues","author":"Shamshirband","year":"2021","journal-title":"J. Biomed. Inform"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.10467","article-title":"Federated multi-task learning","author":"Smith","year":"2017","journal-title":"arXiv preprint arXiv:1705.10467"},{"key":"B29","doi-asserted-by":"publisher","first-page":"5605","DOI":"10.1109\/TII.2020.3034674","article-title":"Adaptive federated learning and digital twin for industrial internet of things","volume":"17","author":"Sun","year":"2020","journal-title":"IEEE Trans. Ind. Inform"},{"key":"B30","doi-asserted-by":"crossref","first-page":"1698","DOI":"10.1109\/INFOCOM41043.2020.9155494","article-title":"\u201cOptimizing federated learning on non-iid data with reinforcement learning,\u201d","volume-title":"IEEE INFOCOM 2020-IEEE Conference on Computer Communications","author":"Wang","year":"2020"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1109\/JSAC.2019.2904348","article-title":"Adaptive federated learning in resource constrained edge computing systems","volume":"37","author":"Wang","year":"2019","journal-title":"IEEE J. Select. Areas Commun"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.3390\/app12178515","article-title":"Lazy aggregation for heterogeneous federated learning","author":"Xu","year":"2022","journal-title":"Appl. Sci"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3183465","article-title":"Optimizing federated learning with deep reinforcement learning for digital twin empowered industrial IoT","author":"Yang","year":"2022","journal-title":"IEEE Trans. Ind. Inform"},{"key":"B34","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1007\/978-3-030-60548-3_15","article-title":"\u201cInverse distance aggregation for federated learning with non-iid data,\u201d","volume-title":"Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning","author":"Yeganeh","year":"2020"},{"key":"B35","first-page":"1","article-title":"\u201cJoint subcarrier and cpu time allocation for mobile edge computing,\u201d","volume-title":"2016 IEEE Global Communications Conference (GLOBECOM)","author":"Yu","year":"2016"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1806.00582","article-title":"Federated learning with non-iid data","author":"Zhao","year":"2018","journal-title":"arXiv preprint arXiv:1806.00582"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2022.1041553\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T12:33:50Z","timestamp":1669293230000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2022.1041553\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,24]]},"references-count":36,"alternative-id":["10.3389\/fnbot.2022.1041553"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2022.1041553","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,24]]},"article-number":"1041553"}}