{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T22:26:51Z","timestamp":1776464811818,"version":"3.51.2"},"reference-count":23,"publisher":"World Scientific Pub Co Pte Ltd","issue":"13","funder":[{"name":"National Key Research and Development Program of China","award":["2018YFB2101300"],"award-info":[{"award-number":["2018YFB2101300"]}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61872147"],"award-info":[{"award-number":["61872147"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J CIRCUIT SYST COMP"],"published-print":{"date-parts":[[2022,9,15]]},"abstract":"<jats:p> As a promising method of central model training on decentralized device data while securing user privacy, Federated Learning (FL) is becoming popular in the Internet of Things (IoT) design. However, when the data collected by IoT devices are highly skewed in a non-independent and identically distributed (non-IID) manner, the accuracy of the vanilla FL method cannot be guaranteed. Although there exist various solutions that try to address the bottleneck of FL with non-IID data, most of them suffer from extra intolerable communication overhead and low model accuracy. To enable fast and accurate FL, this paper proposes a novel data-based device grouping approach that can effectively reduce the disadvantages of weight divergence during the training of non-IID data. However, since our grouping method is based on the similarity of extracted feature maps from IoT devices, it may incur additional risks of privacy exposure. To solve this problem, we propose an improved version by exploiting similarity information using the Locality-Sensitive Hashing (LSH) algorithm without exposing extracted feature maps. Comprehensive experimental results on well-known benchmarks show that our approach can not only accelerate the convergence rate, but also improve the prediction accuracy for FL with non-IID data. <\/jats:p>","DOI":"10.1142\/s0218126622502358","type":"journal-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T10:42:06Z","timestamp":1650883326000},"source":"Crossref","is-referenced-by-count":14,"title":["Towards Fast and Accurate Federated Learning with Non-IID Data for Cloud-Based IoT Applications"],"prefix":"10.1142","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4587-4399","authenticated-orcid":false,"given":"Tian","family":"Liu","sequence":"first","affiliation":[{"name":"MoE Engineering Research Center of SW\/HW Co-Design Technology and Application, East China Normal University, Shanghai 200062, P. R. China"},{"name":"Institution of Information Science and Engineering, Zaozhuang University, Zaozhuang 277160, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Houston, Houston, TX 77204, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Wang","sequence":"additional","affiliation":[{"name":"MoE Engineering Research Center of SW\/HW Co-Design Technology and Application, East China Normal University, Shanghai 200062, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miao","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Houston, Houston, TX 77204, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3922-0989","authenticated-orcid":false,"given":"Mingsong","family":"Chen","sequence":"additional","affiliation":[{"name":"MoE Engineering Research Center of SW\/HW Co-Design Technology and Application, East China Normal University, Shanghai 200062, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2022,5,13]]},"reference":[{"key":"S0218126622502358BIB001","first-page":"1273","volume-title":"Proc. Int. Conf. Artificial Intelligence and Statistics (AISTATS)","volume":"54","author":"McMahan B.","year":"2017"},{"key":"S0218126622502358BIB002","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"S0218126622502358BIB003","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3046665"},{"key":"S0218126622502358BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"key":"S0218126622502358BIB005","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"S0218126622502358BIB006","first-page":"4615","volume-title":"Proc. Int. Conf. Machine Learning (ICML)","volume":"97","author":"Mohri M.","year":"2019"},{"key":"S0218126622502358BIB008","first-page":"1","volume-title":"Proc. Int. Conf. Learning Representations (ICLR)","author":"Li X.","year":"2020"},{"key":"S0218126622502358BIB009","first-page":"3407","volume-title":"Proc. Int. Conf. Machine Learning (ICML)","author":"Fraboni Y.","year":"2021"},{"key":"S0218126622502358BIB011","first-page":"12878","volume-title":"Proc. Int. Conf. Machine Learning (ICML)","author":"Zhu Z.","year":"2021"},{"key":"S0218126622502358BIB012","doi-asserted-by":"publisher","DOI":"10.1142\/S0218126621500250"},{"key":"S0218126622502358BIB013","first-page":"144","volume":"6","author":"Gu H.","year":"2021","journal-title":"IEEE Trans. Comput."},{"key":"S0218126622502358BIB014","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2021.102374"},{"key":"S0218126622502358BIB015","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586175"},{"key":"S0218126622502358BIB016","first-page":"1","volume-title":"Proc. Int. Conf. Learning Representations (ICLR)","author":"Sener O.","year":"2018"},{"key":"S0218126622502358BIB017","first-page":"7865","volume-title":"Proc. Applications of Artificial Intelligence (AAAI)","author":"Huang Y.","year":"2021"},{"key":"S0218126622502358BIB018","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"S0218126622502358BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2942190"},{"key":"S0218126622502358BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.215"},{"key":"S0218126622502358BIB021","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3005969"},{"key":"S0218126622502358BIB022","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2014.2300753"},{"key":"S0218126622502358BIB023","first-page":"634","volume-title":"Proc. Int. Conf. Machine Learning (ICML)","volume":"97","author":"Bhagoji A.","year":"2019"},{"key":"S0218126622502358BIB024","first-page":"518","volume-title":"Proc. Int. Conf. Very Large Data Bases (VLDB)","author":"Gionis A.","year":"1999"},{"key":"S0218126622502358BIB025","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2760458"}],"container-title":["Journal of Circuits, Systems and Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218126622502358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T03:19:20Z","timestamp":1661483960000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218126622502358"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,13]]},"references-count":23,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2022,9,15]]}},"alternative-id":["10.1142\/S0218126622502358"],"URL":"https:\/\/doi.org\/10.1142\/s0218126622502358","relation":{},"ISSN":["0218-1266","1793-6454"],"issn-type":[{"value":"0218-1266","type":"print"},{"value":"1793-6454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,13]]},"article-number":"2250235"}}