{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:44:54Z","timestamp":1785249894566,"version":"3.55.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T00:00:00Z","timestamp":1664496000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>With the widespread use of Internet of things(IoT) devices, it generates an enormous volume of data, and it is a challenge to mine the IoT data value while ensuring security and privacy. Federated learning is a decentralized approach for training data located on edge devices, such as mobile phones and IoT devices, while keeping privacy, efficiency, and security. However, the Non-IID (non-independent and identically distributed) data, always greatly impacts the performance of the global model. In this paper, we propose a FedDynamic algorithm to solve the statistical challenge of federated learning caused by Non-IID. As Non-IID data can lead to significant differences in model parameters between edge devices, we set different weights for different devices during model aggregation to get a high-performance global model. We analyze and exact key indices (local model accuracy, local data quality, and model difference between local models and the global model), which can reflect the quality of the model, and calculate the aggregation weight for edge devices based on the key indices. Furthermore, we dynamically adjust aggregation weight based on accuracy\u2019s variety to solve weight staleness during the training process. Experiments on the MNIST, FMNIST, EMNIST, CINIC-10 and CIFAR-10 datasets show that the FedDynamic algorithm has better accuracy and convergence performance, compared to the FedAvg, FedProx and Scaffold algorithms.<\/jats:p>","DOI":"10.1093\/comjnl\/bxac118","type":"journal-article","created":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T05:46:03Z","timestamp":1664603163000},"page":"2758-2772","source":"Crossref","is-referenced-by-count":43,"title":["Adaptive Federated Learning With Non-IID Data"],"prefix":"10.1093","volume":"66","author":[{"given":"Yan","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University , Hangzhou 310018"},{"name":"Key Laboratory of Complex System Modeling and Simulation, Ministry of Education , Hangzhou 310018"},{"name":"Zhejiang Engineering Research Center of Data Security Governance , Hangzhou 310018"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuankai","family":"Mu","sequence":"additional","affiliation":[{"name":"HDU-ITMO Joint Institute, Hangzhou Dianzi University , Hangzhou 310018"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfeng","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University , Hangzhou 310018"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Teng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University , Hangzhou 310018"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University , Hangzhou 310018"},{"name":"Key Laboratory of Complex System Modeling and Simulation, Ministry of Education , Hangzhou 310018"},{"name":"Zhejiang Engineering Research Center of Data Security Governance , Hangzhou 310018"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University , Hangzhou 310018"},{"name":"Key Laboratory of Complex System Modeling and Simulation, Ministry of Education , Hangzhou 310018"},{"name":"Zhejiang Engineering Research Center of Data Security Governance , Hangzhou 310018"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjian","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University , Hangzhou 310018"},{"name":"Key Laboratory of Complex System Modeling and Simulation, Ministry of Education , Hangzhou 310018"},{"name":"Zhejiang Engineering Research Center of Data Security Governance , Hangzhou 310018"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of computing technology of the Chinese Academy of Sciences , Beijing, 100086"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,9,30]]},"reference":[{"key":"2023111618464993100_ref1","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1109\/COMST.2017.2766698","article-title":"Modulation and multiple access for 5G networks","volume":"20","author":"Cai","year":"2017","journal-title":"IEEE Communications Surveys & Tutorials"},{"key":"2023111618464993100_ref2","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/MCOM.2016.7470940","article-title":"Mobile network architecture evolution toward 5G","volume":"54","author":"Rost","year":"2016","journal-title":"IEEE Communications Magazine"},{"key":"2023111618464993100_ref3","first-page":"1","volume-title":"Proceedings of the 12th ACM workshop on artificial intelligence and security","author":"Truex","year":"2019"},{"key":"2023111618464993100_ref4","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1109\/TIFS.2019.2929409","article-title":"Verifynet: Secure and verifiable federated learning","volume":"15","author":"Xu","year":"2019","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2023111618464993100_ref5","first-page":"13","author":"Xu","year":"2019"},{"key":"2023111618464993100_ref6","first-page":"374","article-title":"Towards federated learning at scale: System design","volume":"1","author":"Bonawitz","year":"2019","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"2023111618464993100_ref7","first-page":"50","article-title":"Federated learning: Challenges, methods, and future directions","volume":"37","author":"Li","year":"2020","journal-title":"IEEE Signal Processing Magazine"},{"key":"2023111618464993100_ref8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3339474","article-title":"Federated machine learning: Concept and applications","volume":"10","author":"Yang","year":"2019","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"2023111618464993100_ref9","first-page":"1000","volume-title":"International conference on machine learning","author":"Shamir","year":"2014"},{"key":"2023111618464993100_ref10","first-page":"1223","volume-title":"Proceedings of the 25th International Conference on Neural Information Processing Systems","author":"","year":"2012"},{"key":"2023111618464993100_ref11","first-page":"19","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems","author":"","year":"2014"},{"key":"2023111618464993100_ref12","first-page":"1273","volume-title":"Artificial intelligence and statistics, Fort Lauderdale, 20\u201322 April 2017","author":"McMahan","year":"2017"},{"key":"2023111618464993100_ref13","article-title":"On the convergence of fedavg on non-iid data","volume-title":"8th International Conference on Learning Representations, Online, April 26\u201330, 2020","author":"Li","year":"2020"},{"key":"2023111618464993100_ref14","first-page":"1223","volume-title":"7th International Conference on Learning Representations, New Orleans, LA, USA, May 6\u20139, 2019","author":"Stich","year":"2019"},{"key":"2023111618464993100_ref15","first-page":"1387","volume-title":"IEEE INFOCOM 2019-IEEE Conference on Computer Communications, Paris, France, April 29 - May 2, 2019","author":"Tran","year":"2019"},{"key":"2023111618464993100_ref16","first-page":"1729","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Hoffer","year":"2017"},{"key":"2023111618464993100_ref17","first-page":"685","article-title":"Deep learning with elastic averaging SGD","volume":"28","author":"Zhang","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023111618464993100_ref18","first-page":"3321","article-title":"Communication-Efficient Algorithms for Statistical Optimization","volume":"14","author":"Zhang","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"2023111618464993100_ref19","article-title":"Federated learning with non-iid data","volume-title":"arXiv Preprint","author":"Zhao","year":"2018"},{"key":"2023111618464993100_ref20","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"2023111618464993100_ref21","first-page":"5132","volume-title":"Proceedings of the 37th International Conference on Machine Learning, 13\u201318 July 2020, Virtual Event","author":"Karimireddy","year":"2020"},{"key":"2023111618464993100_ref22","first-page":"243","article-title":"Don\u2019t Use Large Mini-batches, Use Local SGD","volume":"23","author":"Lin","year":"2019","journal-title":"In International Conference on Learning Representations"},{"key":"2023111618464993100_ref23","first-page":"125","volume-title":"HPDC \u201820: The 29th International Symposium on High-Performance Parallel and Distributed Computing, Stockholm, Sweden, June 23\u201326, 2020","author":"","year":"2020"},{"key":"2023111618464993100_ref24","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.1109\/TC.2021.3099723","article-title":"Adaptive federated learning on non-iid data with resource constraint","volume":"71","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Comput."},{"key":"2023111618464993100_ref25","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume":"33","author":"Fallah","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023111618464993100_ref26","first-page":"12878","volume-title":"Proceedings of the 38th International Conference on Machine Learning, 18\u201324 July 2021, Virtual Event","author":"Zhu","year":"2021"},{"key":"2023111618464993100_ref27","first-page":"231","article-title":"No fear of heterogeneity: Classifier calibration for federated learning with non-iid data","volume":"34","author":"Luo","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023111618464993100_ref28","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"2023111618464993100_ref29","first-page":"4427","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, December 4\u20139, 2017","author":"Smith","year":"2017"},{"key":"2023111618464993100_ref30","first-page":"10713","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li","year":"2021"},{"key":"2023111618464993100_ref31","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":"2023111618464993100_ref32","article-title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","volume-title":"arXiv Preprint","author":"Xiao","year":"2017"},{"key":"2023111618464993100_ref33","first-page":"2921","volume-title":"2017 International Joint Conference on Neural Networks, Anchorage, AK, USA, May 14\u201319, 2017","author":"Cohen","year":"2017"},{"key":"2023111618464993100_ref34","article-title":"CINIC-10 is not imagenet or cifar-10","volume-title":"arXiv Preprint","author":"Darlow","year":"2018"},{"key":"2023111618464993100_ref35","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"2023111618464993100_ref36","article-title":"Fedcd: Improving performance in non-iid federated learning","volume-title":"arXiv Preprint","author":"Kopparapu","year":"2020"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/66\/11\/2758\/53401157\/bxac118.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/66\/11\/2758\/53401157\/bxac118.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T18:47:56Z","timestamp":1700160476000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/66\/11\/2758\/6732678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,30]]},"references-count":36,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2022,9,30]]},"published-print":{"date-parts":[[2023,11,14]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxac118","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,11]]},"published":{"date-parts":[[2022,9,30]]}}}