{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:55:40Z","timestamp":1774018540708,"version":"3.50.1"},"reference-count":16,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"vor","delay-in-days":78,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Communications"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    This study proposes a federated split learning framework for large language models (FedsLLM) integrated with rate\u2010splitting multiple access (RSMA), aimed at enhancing the efficiency and privacy of LLM training in wireless communication systems. By leveraging low\u2010rank adaptation (LoRA) to distribute computational loads and a fluid antenna system to dynamically optimize channel capacity, the framework effectively reduces training latency through joint optimization of learning accuracy and communication resources. Experimental results demonstrate that the proposed framework significantly outperforms traditional time\u2010division multiple access including time division multiple access, frequency division multiple access (FDMA), enhanced bandwidth FDMA, and fairness\u2010enhanced FDMA across multiple metrics: at a transmit power of 20 dBm, RSMA reduces task completion time by 8.3%; under 20 MHz bandwidth, it achieves a 25% performance improvement; and even with a data volume of 900 Kbits, it maintains a 12% advantage. The adopted alternating optimization algorithm converges rapidly, reaching 95% of the optimal value within only 5 iterations, substantially outperforming the fixed\u2010point method. Overall,\n                    <jats:bold>FedsLLM\u2010RSMA<\/jats:bold>\n                    effectively addresses privacy, computational and communication bottlenecks in distributed LLM training. Compared to TDMA, it reduces total training latency by 28% and improves communication efficiency by 35%, while achieving higher model accuracy and faster convergence. This work provides a viable pathway for efficient and scalable deployment of LLMs in\n                    <jats:bold>6G<\/jats:bold>\n                    \u00a0networks.\n                  <\/jats:p>","DOI":"10.1049\/cmu2.70152","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T13:14:22Z","timestamp":1774012462000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Federated Split Learning for Large Language Models With RSMA"],"prefix":"10.1049","volume":"20","author":[{"given":"Jianxin","family":"Dai","sequence":"first","affiliation":[{"name":"College of Science Nanjing University of Posts and Telecommunications Nanjing China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3280-5663","authenticated-orcid":false,"given":"Rui","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Science Nanjing University of Posts and Telecommunications Nanjing China"}]},{"given":"Feibo","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China"}]},{"given":"Zhaohui","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering Zhejiang University Zhejiang China"}]},{"given":"Qianqian","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering Zhejiang University Zhejiang China"}]},{"given":"Zhaoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering Zhejiang University Zhejiang China"}]},{"given":"Linqing","family":"Gui","sequence":"additional","affiliation":[{"name":"School of Computer Nanjing University of Posts and Telecommunications Nanjing China"}]}],"member":"265","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"issue":"3","key":"e_1_2_9_2_1","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1109\/MNET.001.1900287","article-title":"A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems","volume":"34","author":"Saad W.","year":"2019","journal-title":"IEEE Network"},{"issue":"3","key":"e_1_2_9_3_1","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/MVT.2019.2921208","article-title":"6G Wireless Networks: Vision, Requirements, Architecture, and Key Technologies","volume":"14","author":"Zhang Z.","year":"2019","journal-title":"IEEE Vehicular Technology Magazine"},{"issue":"5","key":"e_1_2_9_4_1","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1109\/MWC.015.2300404","article-title":"Big AI Models for 6G Wireless Networks: Opportunities, Challenges, and Research Directions","volume":"31","author":"Chen Z.","year":"2024","journal-title":"IEEE Wireless Communications"},{"issue":"11","key":"e_1_2_9_5_1","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1109\/LCOMM.2019.2934851","article-title":"Deep Learning\u2010Based Downlink Channel Prediction for FDD Massive MIMO System","volume":"23","author":"Yang Y.","year":"2019","journal-title":"IEEE Communications Letters"},{"issue":"7","key":"e_1_2_9_6_1","first-page":"2596","article-title":"Sum\u2010Rate Maximization of Uplink Rate Splitting Multiple Access (RSMA) Communication","volume":"21","author":"Yang Z.","year":"2020","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_2_9_7_1","first-page":"1","article-title":"Rate\u2010Splitting Multiple Access for Downlink Communication Systems: Bridging, Generalizing, and Outperforming SDMA and NOMA","volume":"2018","author":"Mao Y.","year":"2018","journal-title":"EURASIP Journal on Wireless Communications and Networking"},{"issue":"8","key":"e_1_2_9_8_1","doi-asserted-by":"crossref","first-page":"8485","DOI":"10.1609\/aaai.v36i8.20825","article-title":"SplitFed: When Federated Learning Meets Split Learning","volume":"36","author":"Thapa C.","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_2_9_9_1","unstructured":"Z.Zhao Z.Yang Y.Hu Q.Yang W.Xu andZ.Zhang \u201cProbabilistic Semantic Communication Over Wireless Networks With Rate Splitting \u201darXiv:2403.00434(2024)."},{"issue":"2","key":"e_1_2_9_10_1","first-page":"3","article-title":"LORA: Low\u2010Rank Adaptation of Large Language Models","volume":"1","author":"Hu E. J.","year":"2022","journal-title":"The International Conference on Learning Representations"},{"key":"e_1_2_9_11_1","doi-asserted-by":"crossref","unstructured":"A. S.S\u00fcmer M. M.\u015eahin andH.Arslan \u201cAn Efficient Low\u2010Complexity RSMA Scheme for Multi\u2010User Decode\u2010and\u2010Forward Relay Systems \u201darXiv:2409.08880(2024).","DOI":"10.1109\/OJCOMS.2025.3560826"},{"key":"e_1_2_9_12_1","unstructured":"P.Vepakomma O.Gupta T.Swedish andR.Raskar \u201cSplit Learning for Health: Distributed Deep Learning Without Sharing Raw Patient Data \u201darXiv:1812.00564(2018)."},{"key":"e_1_2_9_13_1","doi-asserted-by":"crossref","unstructured":"K.Zhao Z.Yang C.Huang X.Chen andZ.Zhang \u201cFedsLLM: Federated Split Learning for Large Language Models Over Communication Networks \u201d in2024 International Conference on Ubiquitous Communication (UCOM)(IEEE 2024) 438\u2013443.","DOI":"10.1109\/Ucom62433.2024.10695888"},{"issue":"4","key":"e_1_2_9_14_1","doi-asserted-by":"crossref","first-page":"3392","DOI":"10.1109\/TWC.2023.3307696","article-title":"MIMO Capacity Characterization for Movable Antenna Systems","volume":"23","author":"Ma W.","year":"2023","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"e_1_2_9_15_1","article-title":"Hybrid Near\u2010Far Field Channel Estimation for Holographic Mimo Communications","author":"Yue S.","year":"2024","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"e_1_2_9_16_1","doi-asserted-by":"crossref","unstructured":"J.Zhou Y.Yang Z.Yang andM.Shikh\u2010Bahaei \u201cFluid Antenna\u2010Assisted Near\u2010Field System \u201darXiv:2409.20472(2024).","DOI":"10.1109\/GCWkshp64532.2024.11100945"},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","unstructured":"X.Guo Y.Xu D.He C.Zhang W.Zhang andY.\u2010Y.Wu \u201cFluid Antenna Grouping Index Modulation Design for MIMO Systems \u201darXiv:2407.11651(2024).","DOI":"10.1109\/WCNC61545.2025.10978198"}],"container-title":["IET Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cmu2.70152","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cmu2.70152","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cmu2.70152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T13:14:31Z","timestamp":1774012471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cmu2.70152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":16,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/cmu2.70152"],"URL":"https:\/\/doi.org\/10.1049\/cmu2.70152","archive":["Portico"],"relation":{},"ISSN":["1751-8628","1751-8636"],"issn-type":[{"value":"1751-8628","type":"print"},{"value":"1751-8636","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-12-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70152"}}