{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T14:18:46Z","timestamp":1783174726193,"version":"3.54.6"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":[[2026,7]]},"DOI":"10.1016\/j.sysarc.2026.103813","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:28:00Z","timestamp":1778084880000},"page":"103813","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FedCSGA: Evolutionary client selection with joint statistical and system heterogeneity in federated learning"],"prefix":"10.1016","volume":"176","author":[{"given":"Ghani","family":"Haider","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Majid","family":"Kundroo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinchul","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taehong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"10","key":"10.1016\/j.sysarc.2026.103813_b1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3727643","article-title":"A systematic literature review of robust federated learning: Issues, solutions, and future research directions","volume":"57","author":"Uddin","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.sysarc.2026.103813_b2","series-title":"2025 28th International Symposium on Real-Time Distributed Computing","first-page":"265","article-title":"Evaluating federated learning in IoT: Advancing scalability, privacy, and real-time intelligence","author":"Houidi","year":"2025"},{"key":"10.1016\/j.sysarc.2026.103813_b3","series-title":"2024 IEEE 27th International Symposium on Real-Time Distributed Computing","first-page":"1","article-title":"Federated learning models for real-time IoT: A survey","author":"Houidi","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103813_b4","doi-asserted-by":"crossref","DOI":"10.1145\/3735125","article-title":"Bias in federated learning: A comprehensive survey","author":"Benarba","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.sysarc.2026.103813_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.future.2025.108177","article-title":"FedTVD: balancing data quality and quantity for robust federated learning","volume":"176","author":"Selo","year":"2026","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.sysarc.2026.103813_b6","series-title":"Non-iid data in federated learning: A systematic review with taxonomy, metrics, methods, frameworks and future directions","author":"Solans","year":"2024"},{"key":"10.1016\/j.sysarc.2026.103813_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2024.103280","article-title":"DUDS: Diversity-aware unbiased device selection for federated learning on non-IID and unbalanced data","volume":"156","author":"Yu","year":"2024","journal-title":"J. Syst. Archit."},{"key":"10.1016\/j.sysarc.2026.103813_b8","doi-asserted-by":"crossref","DOI":"10.1109\/TPDS.2025.3574718","article-title":"Coordinating computational capacity for adaptive federated learning in heterogeneous edge computing systems","author":"Yang","year":"2025","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.sysarc.2026.103813_b9","article-title":"An empirical study of federated learning on IoT\u2013edge devices: Resource allocation and heterogeneity","author":"Wong","year":"2025","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.sysarc.2026.103813_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2025.103575","article-title":"Efficient dropout-resilient and verifiable federated learning scheme for AIoT healthcare system","volume":"168","author":"Kang","year":"2025","journal-title":"J. Syst. Archit."},{"issue":"2","key":"10.1016\/j.sysarc.2026.103813_b11","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.1007\/s11831-023-10011-4","article-title":"A review of client selection methods in federated learning","volume":"31","author":"Mayhoub","year":"2024","journal-title":"Arch. Comput. Methods Eng."},{"key":"10.1016\/j.sysarc.2026.103813_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2025.103576","article-title":"Balancing privacy and fairness: Client selection in differential privacy-based federated learning","volume":"168","author":"Zhao","year":"2025","journal-title":"J. Syst. Archit."},{"key":"10.1016\/j.sysarc.2026.103813_b13","series-title":"Client selection in federated learning: Convergence analysis and power-of-choice selection strategies","author":"Cho","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103813_b14","series-title":"Active federated learning","author":"Goetz","year":"2019"},{"key":"10.1016\/j.sysarc.2026.103813_b15","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"vol. 2","author":"Li","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103813_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2025.103526","article-title":"When foresight pruning meets zeroth-order optimization: Efficient federated learning for low-memory devices","volume":"168","author":"Zhang","year":"2025","journal-title":"J. Syst. Archit."},{"key":"10.1016\/j.sysarc.2026.103813_b17","doi-asserted-by":"crossref","DOI":"10.1109\/LNET.2024.3363620","article-title":"Greedy Shapley client selection for communication-efficient federated learning","author":"Singhal","year":"2024","journal-title":"IEEE Netw. Lett."},{"key":"10.1016\/j.sysarc.2026.103813_b18","article-title":"Adaptive federated learning with reinforcement learning-based client selection for heterogeneous environments","author":"Ahmed","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.sysarc.2026.103813_b19","series-title":"Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.sysarc.2026.103813_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2022.102413","article-title":"A federated deep learning framework for privacy preservation and communication efficiency","volume":"124","author":"Cao","year":"2022","journal-title":"J. Syst. Archit."},{"key":"10.1016\/j.sysarc.2026.103813_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2025.103569","article-title":"Lightweight multi-layered de-identification architecture: Secure client selection in federated learning","volume":"168","author":"Choi","year":"2025","journal-title":"J. Syst. Archit."},{"key":"10.1016\/j.sysarc.2026.103813_b22","series-title":"ICC 2019-2019 IEEE International Conference on Communications","first-page":"1","article-title":"Client selection for federated learning with heterogeneous resources in mobile edge","author":"Nishio","year":"2019"},{"key":"10.1016\/j.sysarc.2026.103813_b23","series-title":"2025 21st International Conference on Distributed Computing in Smart Systems and the Internet of Things","first-page":"816","article-title":"FedHeur: Multi-heuristic client selection for task offloading in federated learning","author":"Ali","year":"2025"},{"issue":"1","key":"10.1016\/j.sysarc.2026.103813_b24","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1038\/scientificamerican0792-66","article-title":"Genetic algorithms","volume":"267","author":"Holland","year":"1992","journal-title":"Sci. Am."},{"key":"10.1016\/j.sysarc.2026.103813_b25","series-title":"International Conference on Machine Learning","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","author":"Karimireddy","year":"2020"},{"key":"10.1016\/j.sysarc.2026.103813_b26","series-title":"Uncertainty in Artificial Intelligence","first-page":"906","article-title":"Fedvarp: Tackling the variance due to partial client participation in federated learning","author":"Jhunjhunwala","year":"2022"},{"key":"10.1016\/j.sysarc.2026.103813_b27","unstructured":"R. Balakrishnan, T. Li, T. Zhou, N. Himayat, V. Smith, J. Bilmes, Diverse client selection for federated learning via submodular maximization, in: International Conference on Learning Representations, 2022."},{"key":"10.1016\/j.sysarc.2026.103813_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.jpdc.2025.105168","article-title":"HeaPS: Heterogeneity-aware participant selection for efficient federated learning","author":"Yang","year":"2025","journal-title":"J. Parallel Distrib. Comput."},{"issue":"2","key":"10.1016\/j.sysarc.2026.103813_b29","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1109\/JSAIT.2022.3205475","article-title":"Straggler-resilient federated learning: Leveraging the interplay between statistical accuracy and system heterogeneity","volume":"3","author":"Reisizadeh","year":"2022","journal-title":"IEEE J. Sel. Areas Inf. Theory"},{"key":"10.1016\/j.sysarc.2026.103813_b30","article-title":"Addressing data quality decompensation in federated learning via dynamic client selection","author":"Fei","year":"2025","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.sysarc.2026.103813_b31","series-title":"IEEE INFOCOM 2021-IEEE Conference on Computer Communications","first-page":"1","article-title":"Sample-level data selection for federated learning","author":"Li","year":"2021"},{"key":"10.1016\/j.sysarc.2026.103813_b32","series-title":"2019 IEEE 37th International Conference on Computer Design","first-page":"246","article-title":"Astraea: Self-balancing federated learning for improving classification accuracy of mobile deep learning applications","author":"Duan","year":"2019"},{"key":"10.1016\/j.sysarc.2026.103813_b33","series-title":"Federated Learning: Privacy and Incentive","first-page":"108","article-title":"Dealing with label quality disparity in federated learning","author":"Chen","year":"2020"},{"issue":"2","key":"10.1016\/j.sysarc.2026.103813_b34","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1109\/TWC.2020.3031503","article-title":"Client selection and bandwidth allocation in wireless federated learning networks: A long-term perspective","volume":"20","author":"Xu","year":"2020","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"10.1016\/j.sysarc.2026.103813_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106654","article-title":"FedraTrees: A novel computation-communication efficient federated learning framework investigated in smart grids","volume":"124","author":"Al-Quraan","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"3","key":"10.1016\/j.sysarc.2026.103813_b36","doi-asserted-by":"crossref","first-page":"1935","DOI":"10.1109\/TWC.2020.3037554","article-title":"Energy efficient federated learning over wireless communication networks","volume":"20","author":"Yang","year":"2020","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"10.1016\/j.sysarc.2026.103813_b37","series-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.sysarc.2026.103813_b38","series-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"10.1016\/j.sysarc.2026.103813_b39","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"10.1016\/j.sysarc.2026.103813_b40","doi-asserted-by":"crossref","first-page":"104329","DOI":"10.52202\/079017-3314","article-title":"Rflpa: A robust federated learning framework against poisoning attacks with secure aggregation","volume":"37","author":"Mai","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.sysarc.2026.103813_b41","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1038\/s41467-023-44383-9","article-title":"Selective knowledge sharing for privacy-preserving federated distillation without a good teacher","volume":"15","author":"Shao","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.sysarc.2026.103813_b42","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.sysarc.2026.103813_b43","series-title":"Stabilizing federated learning under extreme heterogeneity with hetero-select","author":"Masud","year":"2025"},{"key":"10.1016\/j.sysarc.2026.103813_b44","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"},{"key":"10.1016\/j.sysarc.2026.103813_b45","first-page":"929","article-title":"Pytorch 2: Faster machine learning through dynamic python bytecode transformation and graph compilation","volume":"vol. 2","author":"Ansel","year":"2024"},{"issue":"15","key":"10.1016\/j.sysarc.2026.103813_b46","doi-asserted-by":"crossref","DOI":"10.1007\/s10586-025-05683-5","article-title":"Impact of network topologies on decentralized federated learning","volume":"28","author":"Selo","year":"2025","journal-title":"Clust. Comput."},{"key":"10.1016\/j.sysarc.2026.103813_b47","doi-asserted-by":"crossref","unstructured":"W. Zhao, X. Qiu, J. Fernandez-Marques, P.P. de Gusm\u00e3o, N.D. Lane, Protea: Client profiling within federated systems using flower, in: Proceedings of the 1st ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network, 2022, pp. 1\u20136.","DOI":"10.1145\/3556557.3557950"},{"issue":"4","key":"10.1016\/j.sysarc.2026.103813_b48","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1109\/TEVC.2003.814633","article-title":"Elitism-based compact genetic algorithms","volume":"7","author":"Ahn","year":"2003","journal-title":"IEEE Trans. Evol. Comput."},{"issue":"3","key":"10.1016\/j.sysarc.2026.103813_b49","first-page":"193","article-title":"Genetic algorithms, tournament selection, and the effects of noise","volume":"9","author":"Miller","year":"1995","journal-title":"Complex Systems"},{"key":"10.1016\/j.sysarc.2026.103813_b50","series-title":"2019 IEEE Symposium on Security and Privacy","first-page":"691","article-title":"Exploiting unintended feature leakage in collaborative learning","author":"Melis","year":"2019"},{"key":"10.1016\/j.sysarc.2026.103813_b51","series-title":"2019 IEEE Symposium on Security and Privacy","first-page":"739","article-title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","author":"Nasr","year":"2019"},{"issue":"1\u20132","key":"10.1016\/j.sysarc.2026.103813_b52","first-page":"1","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends\u00ae Mach. Learn."},{"issue":"7","key":"10.1016\/j.sysarc.2026.103813_b53","first-page":"321","article-title":"Algorithm 65: find","volume":"4","author":"Hoare","year":"1961","journal-title":"Commun. ACM"}],"container-title":["Journal of Systems Architecture"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001311?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762126001311?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T13:38:24Z","timestamp":1783172304000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1383762126001311"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":53,"alternative-id":["S1383762126001311"],"URL":"https:\/\/doi.org\/10.1016\/j.sysarc.2026.103813","relation":{},"ISSN":["1383-7621"],"issn-type":[{"value":"1383-7621","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FedCSGA: Evolutionary client selection with joint statistical and system heterogeneity in 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.2026.103813","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":"103813"}}