{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T12:31:22Z","timestamp":1771849882630,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012491","name":"Basic Science Research Program through the National Research Foundation of Korea (NRF), Ministry of Education","doi-asserted-by":"publisher","award":["NRF-2022R1I1A3072355, 50%"],"award-info":[{"award-number":["NRF-2022R1I1A3072355, 50%"]}],"id":[{"id":"10.13039\/501100012491","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovative Human Resource Development for Local Intellectualization Program through the Institute of Information and Communications Technology Planning and Evaluation (IITP), Korean Government","award":["IITP-2024-2020-0-01462, 50%"],"award-info":[{"award-number":["IITP-2024-2020-0-01462, 50%"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3450894","type":"journal-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T19:00:23Z","timestamp":1724871623000},"page":"120570-120583","source":"Crossref","is-referenced-by-count":10,"title":["Demystifying Impact of Key Hyper-Parameters in Federated Learning: A Case Study on CIFAR-10 and FashionMNIST"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4858-1919","authenticated-orcid":false,"given":"Majid","family":"Kundroo","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Chungbuk National University, Cheongju, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6246-6218","authenticated-orcid":false,"given":"Taehong","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Chungbuk National University, Cheongju, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2024.3363670"},{"key":"ref2","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010d n\u00fd","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3262945"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3404948"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3364078"},{"key":"ref6","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist. (AISTATS)","volume":"54","author":"McMahan"},{"key":"ref7","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018","journal-title":"arXiv:1806.00582"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3056919"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-44-319037-7.00021-1"},{"key":"ref10","article-title":"How to privately tune hyperparameters in federated learning? Insights from a benchmark study","author":"Mitic","year":"2024","journal-title":"arXiv:2402.16087"},{"key":"ref11","first-page":"19184","article-title":"Federated hyperparameter tuning: Challenges, baselines, and connections to weight-sharing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Khodak"},{"issue":"9","key":"ref12","article-title":"Federated learning with hyper-parameter optimization","volume":"35","author":"Kundroo","year":"2023","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref13","article-title":"FLoRA: Single-shot hyper-parameter optimization for federated learning","author":"Zhou","year":"2021","journal-title":"arXiv:2112.08524"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3555776.3577847"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref16","article-title":"Adaptive federated optimization","author":"Reddi","year":"2020","journal-title":"arXiv:2003.00295"},{"key":"ref17","article-title":"FedSSO: A federated server-side second-order optimization algorithm","author":"Ma","year":"2022","journal-title":"arXiv:2206.09576"},{"key":"ref18","article-title":"Learning rate adaptation for federated and differentially private learning","author":"Koskela","year":"2018","journal-title":"arXiv:1809.03832"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11723-8_9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426698"},{"key":"ref21","first-page":"9793","article-title":"Adaptive methods for nonconvex optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zaheer"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3299331"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS57198.2023.10188807"},{"key":"ref26","article-title":"Robust federated learning through representation matching and adaptive hyper-parameters","author":"Mostafa","year":"2019","journal-title":"arXiv:1912.13075"},{"key":"ref27","first-page":"1","article-title":"Federated multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Smith"},{"key":"ref28","volume-title":"Machine Learning: A Probabilistic Perspective","author":"Murphy","year":"2012"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.061"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemolab.2022.104520"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1520\/ssms20200029"},{"key":"ref32","article-title":"Dont decay the learning rate, increase the batch size","author":"Smith","year":"2017","journal-title":"arXiv:1711.00489"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1484"},{"key":"ref34","first-page":"20461","article-title":"On large-cohort training for federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Charles"},{"issue":"1","key":"ref35","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/TMC.2021.3075291","article-title":"Adaptive batch size for federated learning in resource-constrained edge computing","volume":"22","author":"Ma","year":"2023","journal-title":"IEEE Trans. Mobile Comput."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM55135.2022.10017717"},{"key":"ref37","first-page":"1","article-title":"On noisy evaluation in federated hyperparameter tuning","volume-title":"Proc. Mach. Learn. Syst.","volume":"5","author":"Kuo"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3261266"},{"issue":"1","key":"ref39","first-page":"26","article-title":"Hyperparameter optimization for machine learning models based on Bayesian optimization","volume":"17","author":"Wu","year":"2019","journal-title":"J. Electron. Sci. Technol."},{"key":"ref40","article-title":"Flower: A friendly federated learning research framework","author":"Beutel","year":"2020","journal-title":"arXiv:2007.14390"},{"key":"ref41","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref42","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2022.3226860"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10654271.pdf?arnumber=10654271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T04:35:17Z","timestamp":1725770117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10654271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3450894","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}