{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T01:19:24Z","timestamp":1783041564815,"version":"3.54.6"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute of Information & Communications Technology Planning & Evaluation","doi-asserted-by":"publisher","award":["RS-2025-02217801"],"award-info":[{"award-number":["RS-2025-02217801"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems Architecture"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.sysarc.2026.103843","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T06:06:46Z","timestamp":1779084406000},"page":"103843","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FedChyper: Client-side dynamic hyper-parameter tuning for enhanced federated learning"],"prefix":"10.1016","volume":"177","author":[{"given":"Majid","family":"Kundroo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seong Hoon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taehong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.sysarc.2026.103843_b1","series-title":"Federated Learning: Strategies for Improving Communication Efficiency","first-page":"1","author":"Kone\u010dn\u00fd","year":"2016"},{"key":"10.1016\/j.sysarc.2026.103843_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.130487","article-title":"FedLBW: A loss-based weighting strategy for federated learning on non-IID data in wireless networks","volume":"302","author":"Kundroo","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.sysarc.2026.103843_b3","doi-asserted-by":"crossref","first-page":"6194","DOI":"10.1109\/ACCESS.2025.3648805","article-title":"FedMeanStd: Federated aggregation with outliers filtering","volume":"14","author":"Singh","year":"2026","journal-title":"IEEE Access"},{"issue":"C","key":"10.1016\/j.sysarc.2026.103843_b4","article-title":"FedCust: Offloading hyperparameter customization for federated learning","volume":"167","author":"Zawad","year":"2025","journal-title":"Perform. Eval."},{"key":"10.1016\/j.sysarc.2026.103843_b5","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1016\/j.future.2024.04.047","article-title":"Elastic federated learning with kubernetes vertical pod autoscaler for edge computing","volume":"158","author":"Pham","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.sysarc.2026.103843_b6","series-title":"Hyper-Parameter Optimization: A Review of Algorithms and Applications","first-page":"1","author":"Yu","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103843_b7","doi-asserted-by":"crossref","first-page":"120570","DOI":"10.1109\/ACCESS.2024.3450894","article-title":"Demystifying impact of key hyper-parameters in federated learning: A case study on CIFAR-10 and fashionmnist","volume":"12","author":"Kundroo","year":"2024","journal-title":"IEEE Access"},{"issue":"null","key":"10.1016\/j.sysarc.2026.103843_b8","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.sysarc.2026.103843_b9","first-page":"1","article-title":"Algorithms for hyper-parameter optimization","volume":"vol. 24","author":"Bergstra","year":"2011"},{"key":"10.1016\/j.sysarc.2026.103843_b10","doi-asserted-by":"crossref","unstructured":"K.K. Nakka, A. Frikha, R. Mendis, X. Jiang, X. Zhou, Federated Hyperparameter Optimization Through Reward-Based Strategies: Challenges and Insights, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 4236\u20134244.","DOI":"10.1109\/CVPRW63382.2024.00427"},{"issue":"5","key":"10.1016\/j.sysarc.2026.103843_b11","doi-asserted-by":"crossref","first-page":"1116","DOI":"10.1109\/TNN.2006.878121","article-title":"On adaptive learning rate that guarantees convergence in feedforward networks","volume":"17","author":"Behera","year":"2006","journal-title":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.sysarc.2026.103843_b12","article-title":"Communication-efficient learning of deep networks from decentralized data","volume":"vol. 54","author":"Brendan McMahan","year":"2017"},{"key":"10.1016\/j.sysarc.2026.103843_b13","series-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"10.1016\/j.sysarc.2026.103843_b14","series-title":"Federated Optimization in Heterogeneous Networks","author":"Li","year":"2018"},{"key":"10.1016\/j.sysarc.2026.103843_b15","series-title":"International Conference on Machine Learning","first-page":"19767","article-title":"Revisiting weighted aggregation in federated learning with neural networks","author":"Li","year":"2023"},{"issue":"NeurIPS","key":"10.1016\/j.sysarc.2026.103843_b16","first-page":"19184","article-title":"Federated Hyperparameter Tuning: Challenges, Baselines, and Connections toWeight-Sharing","volume":"23","author":"Khodak","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.sysarc.2026.103843_b17","series-title":"ICC 2025 - IEEE International Conference on Communications","first-page":"801","article-title":"FedABC: Attention-based client selection for federated learning with long-term view","author":"Ye","year":"2025"},{"key":"10.1016\/j.sysarc.2026.103843_b18","series-title":"Automated Machine Learning","first-page":"3","article-title":"Hyperparameter optimization","author":"Feurer","year":"2019"},{"issue":"4","key":"10.1016\/j.sysarc.2026.103843_b19","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1109\/TNSE.2021.3056655","article-title":"FLAS: Computation and Communication Efficient Federated Learning via Adaptive Sampling","volume":"9","author":"Shu","year":"2022","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"10.1016\/j.sysarc.2026.103843_b20","series-title":"Proceedings of the 40th International Conference on Machine Learning","first-page":"14039","article-title":"Achieving linear speedup in non-IID federated bilevel learning","author":"Huang","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103843_b21","article-title":"Solving a class of non-convex minimax optimization in federated learning","volume":"36","author":"Wu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.sysarc.2026.103843_b22","series-title":"Proceedings of the Nineteenth European Conference on Computer Systems","first-page":"200","article-title":"FLOAT: Federated learning optimizations with automated tuning","author":"Khan","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103843_b23","series-title":"Practical Bayesian optimization of machine learning algorithms","author":"Snoek","year":"2012"},{"key":"10.1016\/j.sysarc.2026.103843_b24","series-title":"Adaptive federated optimization","author":"Reddi","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103843_b25","series-title":"Flora: Single-shot hyper-parameter optimization for federated learning","author":"Zhou","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103843_b26","series-title":"FEATHERS: Federated architecture and hyperparameter search","author":"Seng","year":"2023"},{"key":"10.1016\/j.sysarc.2026.103843_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.jksuci.2023.101740","article-title":"Federated learning with hyper-parameter optimization","author":"Kundroo","year":"2023","journal-title":"J. King Saud University-Computer Inf. Sci."},{"key":"10.1016\/j.sysarc.2026.103843_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126354","article-title":"Federated learning framework based on trimmed mean aggregation rules","volume":"270","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.sysarc.2026.103843_b29","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.neucom.2020.07.061","article-title":"On hyperparameter optimization of machine learning algorithms: Theory and practice","volume":"415","author":"Yang","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.sysarc.2026.103843_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.121641","article-title":"Privacy-preserving and communication-efficient stochastic alternating direction method of multipliers for federated learning","volume":"691","author":"Zhang","year":"2025","journal-title":"Inform. Sci."},{"key":"10.1016\/j.sysarc.2026.103843_b31","series-title":"Learning multiple layers of features from tiny images.(2009)","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.sysarc.2026.103843_b32","series-title":"Leaf: A benchmark for federated settings","author":"Caldas","year":"2018"},{"key":"10.1016\/j.sysarc.2026.103843_b33","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.sysarc.2026.103843_b34","series-title":"Neural Networks: Tricks of the Trade","first-page":"55","article-title":"Early stopping-but when?","author":"Prechelt","year":"1998"},{"key":"10.1016\/j.sysarc.2026.103843_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.softx.2025.102276","article-title":"FedEasy : Federated learning with ease","volume":"31","author":"Kundroo","year":"2025","journal-title":"SoftwareX"}],"container-title":["Journal of Systems Architecture"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S138376212600161X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S138376212600161X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:40:33Z","timestamp":1783039233000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S138376212600161X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":35,"alternative-id":["S138376212600161X"],"URL":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103843","relation":{},"ISSN":["1383-7621"],"issn-type":[{"value":"1383-7621","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FedChyper: Client-side dynamic hyper-parameter tuning for enhanced federated learning","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems Architecture","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103843","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103843"}}