{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T21:06:25Z","timestamp":1774904785085,"version":"3.50.1"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100014189","name":"Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry","doi-asserted-by":"publisher","award":["RS-2024-00397026"],"award-info":[{"award-number":["RS-2024-00397026"]}],"id":[{"id":"10.13039\/501100014189","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["IITP-2025-RS-2022-00156287"],"award-info":[{"award-number":["IITP-2025-RS-2022-00156287"]}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["IITP-2025-RS-2023-00256629"],"award-info":[{"award-number":["IITP-2025-RS-2023-00256629"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3676500","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:09:20Z","timestamp":1774296560000},"page":"44755-44774","source":"Crossref","is-referenced-by-count":0,"title":["ATC-FL: Adaptive Thompson Sampling for Efficient Clustering in Federated Learning"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8422-6071","authenticated-orcid":false,"given":"Shivani Sanjay","family":"Kolekar","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8108-6268","authenticated-orcid":false,"given":"Jisoo","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5413-6710","authenticated-orcid":false,"given":"David J.","family":"Richter","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9985-3051","authenticated-orcid":false,"given":"Kyungbaek","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref2","first-page":"5526","article-title":"Personalized federated learning for cross-city traffic prediction","volume-title":"Proc. 33rd IJCAI","author":"Zhang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29467"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103270"},{"issue":"14","key":"ref5","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Tian","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref6","first-page":"19","article-title":"Oort: Efficient federated learning via guided participant selection","volume-title":"Proc. 15th Symp. Operating Syst. Design Implement.","author":"Lai"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/APNOMS67058.2025.11181385"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS57970.2025.11073667"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2024.3379933"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3594739.3612913"},{"key":"ref11","first-page":"1","article-title":"Analysis of Thompson sampling for the multiarmed bandit problem","volume-title":"Proc. Conf. Learn. Theory","author":"Agrawal"},{"key":"ref12","article-title":"Bayesian fixedbudget best-arm identification","author":"Atsidakou","year":"2022","journal-title":"arXiv:2211.08572"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tsmcb.2012.2188509"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.111002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/55482.55502"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868466"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3366947"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS55811.2022.00011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20785"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3192506"},{"key":"ref23","first-page":"3407","article-title":"Clustered sampling: Low-variance and improved representativity for clients selection in federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fraboni"},{"key":"ref24","first-page":"271","article-title":"Optimizing cluster head placement in federated clustering: A genetic algorithm approach","volume-title":"Proc. 24th Asia\u2013Pacific Netw. Oper. Manag. Symp.","author":"Kolekar"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761315"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392686"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2006.03.005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00010"},{"key":"ref29","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018","journal-title":"arXiv:1803.05407"},{"key":"ref30","article-title":"Adaptive federated optimization","author":"Reddi","year":"2020","journal-title":"arXiv:2003.00295"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/16m1080173"},{"key":"ref33","article-title":"Local SGD converges fast and communicates little","author":"Stich","year":"2018","journal-title":"arXiv:1805.09767"},{"key":"ref34","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Machine Learn.","author":"Karimireddy"},{"key":"ref35","first-page":"10334","article-title":"Is local SGD better than minibatch SGD?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Woodworth"},{"key":"ref36","first-page":"5834","article-title":"Federated learning under distributed concept drift","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Jothimurugesan"},{"key":"ref37","article-title":"On the convergence of local descent methods in federated learning","author":"Haddadpour","year":"2019","journal-title":"arXiv:1910.14425"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(96)00127-6"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/565117.565124"},{"key":"ref40","article-title":"The error-feedback framework: Better rates for SGD with delayed gradients and compressed communication","author":"Stich","year":"2019","journal-title":"arXiv:1909.05350"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"issue":"134","key":"ref42","first-page":"1","article-title":"Stochastic gradient descent as approximate Bayesian inference","volume":"18","author":"Stephan","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3088510"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_18"},{"key":"ref45","first-page":"1","article-title":"An information-theoretic analysis for Thompson sampling with many actions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref46","first-page":"1","article-title":"Sparsified SGD with memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Stich"},{"key":"ref47","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"Lin","year":"2017","journal-title":"arXiv:1712.01887"},{"key":"ref48","first-page":"913","article-title":"Sadagrad: Strongly adaptive stochastic gradient methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/e26121099"},{"key":"ref50","first-page":"1","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dan"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1079120130"},{"key":"ref52","article-title":"Flower: A friendly federated learning research framework","author":"Beutel","year":"2020","journal-title":"arXiv:2007.14390"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291210"},{"key":"ref54","article-title":"Human activity recognition using smartphones","author":"Reyes-Ortiz","year":"2012"},{"issue":"1","key":"ref55","first-page":"3","article-title":"A public domain dataset for human activity recognition using smartphones","volume-title":"Proc. Esann","volume":"3","author":"Anguita"},{"key":"ref56","article-title":"Learning multiple layers of features from tiny images","author":"Alex","year":"2009"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS.2014.6838227"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0103-9"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.v7i3.405"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref63","article-title":"Large language models can be strong differentially private learners","author":"Li","year":"2021","journal-title":"arXiv:2110.05679"},{"key":"ref64","article-title":"Differentially private federated learning: A client level perspective","author":"Geyer","year":"2017","journal-title":"arXiv:1712.07557"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/1592568.1592576"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1985.6312192"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-024-00322-3"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3390\/s22031002"},{"key":"ref69","first-page":"11814","article-title":"Fedscale: Benchmarking model and system performance of federated learning at scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lai"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629575"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.scico.2019.102343"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM.2017.8256059"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-49390-8_61"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS.2014.6838228"},{"key":"ref75","article-title":"Federated learning with personalization layers","author":"Ghuhan Arivazhagan","year":"2019","journal-title":"arXiv:1912.00818"},{"key":"ref76","first-page":"9687","article-title":"Federated Bayesian optimization via Thompson sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref77","article-title":"Adaptive federated learning with auto-tuned clients via local smoothness","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref78","first-page":"8133","article-title":"Rethinking gradient sparsification as total error minimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Atal"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3037554"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3501297"},{"key":"ref81","first-page":"3581","article-title":"Federated learning with buffered asynchronous aggregation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Nguyen"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563463"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1128"},{"key":"ref85","article-title":"Orchestra: Unsupervised federated learning via globally consistent clustering","author":"Singh Lubana","year":"2022","journal-title":"arXiv:2205.11506"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11450082.pdf?arnumber=11450082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T20:08:32Z","timestamp":1774901312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11450082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3676500","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}