{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:52:29Z","timestamp":1786121549965,"version":"build-2736575974"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2026-25497760"],"award-info":[{"award-number":["RS-2026-25497760"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134671","type":"journal-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T23:26:20Z","timestamp":1785367580000},"page":"134671","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FedSplitX: Federated split learning for computationally-constrained heterogeneous clients"],"prefix":"10.1016","volume":"702","author":[{"given":"Jiyun","family":"Shin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joonwoo","family":"Bae","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2138-8641","authenticated-orcid":false,"given":"Honggu","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9737-0432","authenticated-orcid":false,"given":"Seongah","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1863-121X","authenticated-orcid":false,"given":"Jin-Hyun","family":"Ahn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134671_bib0005","series-title":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","first-page":"671","article-title":"JALAD: joint accuracy-and latency-aware deep structure decoupling for edge-cloud execution","author":"Li","year":"2018"},{"key":"10.1016\/j.neucom.2026.134671_bib0010","series-title":"IEEE INFOCOM 2024-IEEE Conference on Computer Communications","first-page":"1001","article-title":"Galaxy: a resource-efficient collaborative edge AI system for in-situ transformer inference","author":"Ye","year":"2024"},{"key":"10.1016\/j.neucom.2026.134671_bib0015","author":"Bommasani"},{"key":"10.1016\/j.neucom.2026.134671_bib0020","author":"Touvron"},{"key":"10.1016\/j.neucom.2026.134671_bib0025","author":"Vepakomma"},{"key":"10.1016\/j.neucom.2026.134671_bib0030","series-title":"ICML 2021 Workshop on Federated Learning for User Privacy and Data Confidentiality","article-title":"Accelerating federated learning with split learning on locally generated losses","author":"Han","year":"2021"},{"key":"10.1016\/j.neucom.2026.134671_bib0035","series-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.neucom.2026.134671_bib0040","series-title":"AAAI Conference on Artificial Intelligence (AAAI)","article-title":"SplitFed: when federated learning meets split learning","author":"Thapa","year":"2022"},{"issue":"9","key":"10.1016\/j.neucom.2026.134671_bib0045","doi-asserted-by":"crossref","first-page":"15587","DOI":"10.1109\/JIOT.2024.3350241","article-title":"FedSL: a communication-efficient federated learning with split layer aggregation","volume":"11","author":"Zhang","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.neucom.2026.134671_bib0050","series-title":"ICC 2023-IEEE International Conference on Communications","first-page":"2976","article-title":"Communication and storage efficient federated split learning","author":"Mu","year":"2023"},{"issue":"6","key":"10.1016\/j.neucom.2026.134671_bib0055","doi-asserted-by":"crossref","first-page":"5587","DOI":"10.1109\/TWC.2023.3327372","article-title":"Accelerating split federated learning over wireless communication networks","volume":"23","author":"Xu","year":"2023","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"5","key":"10.1016\/j.neucom.2026.134671_bib0060","doi-asserted-by":"crossref","first-page":"1380","DOI":"10.1109\/TBDATA.2023.3280405","article-title":"Privacy and efficiency of communications in federated split learning","volume":"9","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Big Data"},{"issue":"1","key":"10.1016\/j.neucom.2026.134671_bib0065","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1109\/TVT.2023.3304176","article-title":"Federated split learning with data and label privacy preservation in vehicular networks","volume":"73","author":"Wu","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"6","key":"10.1016\/j.neucom.2026.134671_bib0070","doi-asserted-by":"crossref","first-page":"7048","DOI":"10.1109\/TMC.2023.3331690","article-title":"Federated split learning with joint personalization-generalization for inference-stage optimization in wireless edge networks","volume":"23","author":"Han","year":"2023","journal-title":"IEEE Trans. Mob. Comput."},{"issue":"9","key":"10.1016\/j.neucom.2026.134671_bib0075","doi-asserted-by":"crossref","first-page":"14110","DOI":"10.1109\/TITS.2025.3554710","article-title":"PSFL: personalized split federated learning framework for distributed model training in intelligent transportation systems","volume":"26","author":"Dai","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"22","key":"10.1016\/j.neucom.2026.134671_bib0080","doi-asserted-by":"crossref","first-page":"47069","DOI":"10.1109\/JIOT.2025.3601814","article-title":"Personalized split federated learning with early-exit: pre-training and online learning against label shifts","volume":"12","author":"Kim","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.neucom.2026.134671_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.106775","article-title":"A survey on federated learning","volume":"216","author":"Zhang","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.134671_bib0090","series-title":"International Conference on Learning Representations (ICLR)","article-title":"HeteroFL: computation and communication efficient federated learning for heterogeneous clients","author":"Diao","year":"2021"},{"key":"10.1016\/j.neucom.2026.134671_bib0095","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"FjORD: fair and accurate federated learning under heterogeneous targets with ordered dropout","author":"Horv\u00e1th","year":"2021"},{"key":"10.1016\/j.neucom.2026.134671_bib0100","series-title":"International Conference on Learning Representations (ICLR)","article-title":"DepthFL: depthwise federated learning for heterogeneous clients","author":"Kim","year":"2023"},{"issue":"8","key":"10.1016\/j.neucom.2026.134671_bib0105","doi-asserted-by":"crossref","first-page":"6734","DOI":"10.1109\/TMC.2025.3549600","article-title":"NeFL: nested model scaling for federated learning with system heterogeneous clients","volume":"24","author":"Kang","year":"2025","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.neucom.2026.134671_bib0110","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"24532","article-title":"ScaleFL: resource-adaptive federated learning with heterogeneous clients","author":"Ilhan","year":"2023"},{"key":"10.1016\/j.neucom.2026.134671_bib0115","author":"Sun"},{"issue":"4","key":"10.1016\/j.neucom.2026.134671_bib0120","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1109\/JSAC.2023.3242704","article-title":"Split learning over wireless networks: parallel design and resource management","volume":"41","author":"Wu","year":"2023","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"10.1016\/j.neucom.2026.134671_bib0125","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3547641","article-title":"A comprehensive survey on split-fed learning: methods, innovations, and future directions","volume":"13","author":"Hukkeri","year":"2025","journal-title":"IEEE Access"},{"issue":"16","key":"10.1016\/j.neucom.2026.134671_bib0130","doi-asserted-by":"crossref","first-page":"27153","DOI":"10.1109\/JIOT.2024.3397677","article-title":"ESFL: efficient split federated learning over resource-constrained heterogeneous wireless devices","volume":"11","author":"Zhu","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.neucom.2026.134671_bib0135","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1109\/TMLCN.2024.3409205","article-title":"DFL: dynamic federated split learning in heterogeneous IoT","volume":"2","author":"Samikwa","year":"2024","journal-title":"IEEE Trans. Mach. Learn. Commun. Netw."},{"key":"10.1016\/j.neucom.2026.134671_bib0140","author":"Nair"},{"issue":"6","key":"10.1016\/j.neucom.2026.134671_bib0145","doi-asserted-by":"crossref","first-page":"2993","DOI":"10.1109\/TON.2025.3577790","article-title":"Adaptsfl: adaptive split federated learning in resource-constrained edge networks","volume":"33","author":"Lin","year":"2025","journal-title":"IEEE Trans. Netw."},{"key":"10.1016\/j.neucom.2026.134671_bib0150","doi-asserted-by":"crossref","first-page":"1981","DOI":"10.1109\/TWC.2025.3594006","article-title":"Communication-and-computation efficient split federated learning in wireless networks: gradient aggregation and resource management","volume":"25","author":"Liang","year":"2026","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"10.1016\/j.neucom.2026.134671_bib0155","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134671_bib0160","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5188","article-title":"Understanding deep image representations by inverting them","author":"Mahendran","year":"2015"},{"key":"10.1016\/j.neucom.2026.134671_bib0165","series-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"Socher","year":"2013"},{"key":"10.1016\/j.neucom.2026.134671_bib0170","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134671_bib0175","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134671_bib0180","author":"Sah"},{"key":"10.1016\/j.neucom.2026.134671_bib0185","author":"Swaminathan"},{"key":"10.1016\/j.neucom.2026.134671_bib0190","series-title":"Proceedings of the International Conference on Learning Representations (ICLR)","article-title":"PalmBench: a comprehensive benchmark of compressed large language models on mobile platforms","author":"Li","year":"2025"},{"key":"10.1016\/j.neucom.2026.134671_bib0195","series-title":"Proceedings of the 30th Annual International Conference on Mobile Computing and Networking (MobiCom)","first-page":"932","article-title":"MELTing point: mobile evaluation of language transformers","author":"Laskaridis","year":"2024"},{"key":"10.1016\/j.neucom.2026.134671_bib0200","author":"Shwartz-Ziv"},{"key":"10.1016\/j.neucom.2026.134671_bib0205","series-title":"Elements of Information Theory","author":"Cover","year":"2006"},{"issue":"3","key":"10.1016\/j.neucom.2026.134671_bib0210","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1142\/S1793351X16500045","article-title":"Deep learning","volume":"10","author":"Hao","year":"2016","journal-title":"Int. J. Semant. Comput."},{"key":"10.1016\/j.neucom.2026.134671_bib0215","author":"Oymak"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020692?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226020692?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T05:31:54Z","timestamp":1786080714000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226020692"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":43,"alternative-id":["S0925231226020692"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134671","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FedSplitX: Federated split learning for computationally-constrained heterogeneous clients","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134671","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":"134671"}}