{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T05:32:40Z","timestamp":1782624760723,"version":"3.54.5"},"reference-count":45,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union\u2014Next Generation EU\u2014under the Italian National Recovery and Resilience Plan (NRRP)","award":["Mission 4, Component 2, Investment 1.3, CUP B83C22004870007, partnership on \u201cTelecommunications of the Future\u201d (PE00000001-program \u201cRESTART\u201d)"],"award-info":[{"award-number":["Mission 4, Component 2, Investment 1.3, CUP B83C22004870007, partnership on \u201cTelecommunications of the Future\u201d (PE00000001-program \u201cRESTART\u201d)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Network"],"abstract":"<jats:p>The successful integration of Terrestrial and Non-Terrestrial Networks (T\/NTNs) in 6G is poised to revolutionize demanding domains like Earth Observation (EO) and Intelligent Transportation Systems (ITSs). Still, it requires Distributed Machine Learning (DML) frameworks that are scalable, private, and efficient. Existing methods, such as Federated Learning (FL) and Split Learning (SL), face critical limitations in terms of client computation burden and latency. To address these challenges, this paper proposes a novel hierarchical DML paradigm. We first introduce Federated Split Transfer Learning (FSTL), a foundational framework that synergizes FL, SL, and Transfer Learning (TL) to enable efficient, privacy-preserving learning within a single client group. We then extend this concept to the Generalized FSTL (GFSTL) framework, a scalable, multi-group architecture designed for complex and large-scale networks. GFSTL orchestrates parallel training across multiple client groups managed by intermediate servers (RSUs\/HAPs) and aggregates them at a higher-level central server, significantly enhancing performance. We apply this framework to a unified T\/NTN architecture that seamlessly integrates vehicular, aerial, and satellite assets, enabling advanced applications in 6G ITS and EO. Comprehensive simulations using the YOLOv5 model on the Cityscapes dataset validate our approach. The results show that GFSTL not only achieves faster convergence and higher detection accuracy but also substantially reduces communication overhead compared to baseline FL, and critically, both detection accuracy and end-to-end latency remain essentially invariant as the number of participating users grows, making GFSTL especially well suited for large-scale heterogeneous 6G ITS deployments. We also provide a formal latency decomposition and analysis that explains this scaling behavior. This work establishes GFSTL as a robust and practical solution for enabling the intelligent, connected, and resilient ecosystems required for next-generation transportation and environmental monitoring.<\/jats:p>","DOI":"10.3390\/network5030041","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T14:10:19Z","timestamp":1758118219000},"page":"41","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Unified Distributed Machine Learning for 6G Intelligent Transportation Systems: A Hierarchical Approach for Terrestrial and Non-Terrestrial Networks"],"prefix":"10.3390","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0767-7622","authenticated-orcid":false,"given":"David","family":"Naseh","sequence":"first","affiliation":[{"name":"Department of Electrical, Electronic and Information Engineering, University of Bologna, 40136 Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1360-6952","authenticated-orcid":false,"given":"Arash","family":"Bozorgchenani","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Leeds, Leeds LS2 9JT, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2716-6441","authenticated-orcid":false,"given":"Swapnil Sadashiv","family":"Shinde","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, 11428 Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7338-1957","authenticated-orcid":false,"given":"Daniele","family":"Tarchi","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Florence, 50139 Florence, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1109\/JPROC.2019.2954595","article-title":"Future Intelligent and Secure Vehicular Network Toward 6G: Machine-Learning Approaches","volume":"108","author":"Tang","year":"2020","journal-title":"Proc. IEEE"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Brincat, A.A., Pacifici, F., Martinaglia, S., and Mazzola, F. (2019, January 15\u201318). The Internet of Things for Intelligent Transportation Systems in Real Smart Cities Scenarios. Proceedings of the 2019 IEEE 5th World Forum on Internet of Things (WF-IoT), Limerick, Ireland.","DOI":"10.1109\/WF-IoT.2019.8767247"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1016\/j.future.2013.01.010","article-title":"Internet of Things (IoT): A vision, architectural elements, and future directions","volume":"29","author":"Gubbi","year":"2013","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"15679","DOI":"10.1109\/ACCESS.2018.2815989","article-title":"Fog Based Intelligent Transportation Big Data Analytics in The Internet of Vehicles Environment: Motivations, Architecture, Challenges, and Critical Issues","volume":"6","author":"Darwish","year":"2018","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Yurdem, B., Kuzlu, M., Gullu, M.K., Catak, F.O., and Tabassum, M. (2024). Federated learning: Overview, strategies, applications, tools and future directions. Heliyon, 10.","DOI":"10.1016\/j.heliyon.2024.e38137"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"17613","DOI":"10.1109\/TVT.2024.3427349","article-title":"Optimized Federated Multitask Learning in Mobile Edge Networks: A Hybrid Client Selection and Model Aggregation Approach","volume":"73","author":"Hamood","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_7","first-page":"1","article-title":"Privacy and Fairness in Federated Learning: On the Perspective of Tradeoff","volume":"56","author":"Chen","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2538","DOI":"10.1109\/TC.2021.3135752","article-title":"Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things","volume":"71","author":"Gao","year":"2022","journal-title":"IEEE Trans. Comput."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2650","DOI":"10.1109\/TWC.2022.3213411","article-title":"Wireless Distributed Learning: A New Hybrid Split and Federated Learning Approach","volume":"22","author":"Liu","year":"2023","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Vilalta, R., and Meskhi, M.M. (2022). Transfer of Knowledge Across Tasks. Metalearning: Applications to Automated Machine Learning and Data Mining, Springer International Publishing.","DOI":"10.1007\/978-3-030-67024-5_12"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1109\/TGCN.2022.3233825","article-title":"A Resource-Efficient Cross-Domain Sensing Method for Device-Free Gesture Recognition With Federated Transfer Learning","volume":"7","author":"Qi","year":"2023","journal-title":"Trans. Green Commun. Netw."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"33","DOI":"10.5194\/isprs-archives-XLVIII-4-W7-2023-33-2023","article-title":"Digital earth observation infrastructures and initiatives: A review framework based on open principles","volume":"48","author":"Leo","year":"2023","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.inffus.2020.07.004","article-title":"Machine learning information fusion in Earth observation: A comprehensive review of methods, applications and data sources","volume":"63","author":"Ghamisi","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/MAES.2020.3049030","article-title":"Machine Learning\/Artificial Intelligence for Sensor Data Fusion\u2013Opportunities and Challenges","volume":"36","author":"Blasch","year":"2021","journal-title":"IEEE Aerosp. Electron. Syst. Mag."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"10564","DOI":"10.1109\/TITS.2024.3362515","article-title":"6G Enabled Advanced Transportation Systems","volume":"25","author":"Liu","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Djihane, M., Abdelkrim, H., and Mohamed, B. (2024, January 21\u201322). Exploring the potential of Non Terrestrial Networks in next generation Intelligent Transport Systems. Proceedings of the 2024 8th International Conference on Image and Signal Processing and Their Applications (ISPA), Biskra, Algeria.","DOI":"10.1109\/ISPA59904.2024.10536838"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Dai, C., Zhu, T., Xiang, S., Xie, L., Garg, S., and Hossain, M.S. (2025). PSFL: Personalized Split Federated Learning Framework for Distributed Model Training in Intelligent Transportation Systems. IEEE Trans. Intell. Transp. Syst., 1\u201310. early access.","DOI":"10.1109\/TITS.2025.3554710"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"7462","DOI":"10.1109\/TITS.2022.3159092","article-title":"On the Feasibility of Split Learning, Transfer Learning and Federated Learning for Preserving Security in ITS Systems","volume":"24","author":"Otoum","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_19","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":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_20","unstructured":"Naseh, D., Shinde, S.S., and Tarchi, D. (2023, January 2\u20134). Enabling Intelligent Vehicular Networks Through Distributed Learning in the Non-Terrestrial Networks 6G Vision. Proceedings of the European Wireless 2023 (EW 2023), Rome, Italy."},{"key":"ref_21","first-page":"1384","article-title":"YOLO-Based Vehicle Detection: Literature Review","volume":"6","author":"Kosasi","year":"2024","journal-title":"J. Comput. Networks, Archit. High Perform. Comput."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Naseh, D., Shinde, S.S., and Tarchi, D. (2024). Network Sliced Distributed Learning-as-a-Service for Internet of Vehicles Applications in 6G Non-Terrestrial Network Scenarios. J. Sens. Actuator Netw., 13.","DOI":"10.3390\/jsan13010014"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ridolfi, L., Naseh, D., Shinde, S.S., and Tarchi, D. (2023). Implementation and Evaluation of a Federated Learning Framework on Raspberry PI Platforms for IoT 6G Applications. Future Internet, 15.","DOI":"10.3390\/fi15110358"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.future.2023.09.008","article-title":"Model aggregation techniques in federated learning: A comprehensive survey","volume":"150","author":"Qi","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"101251","DOI":"10.1016\/j.iot.2024.101251","article-title":"A contemporary survey of recent advances in federated learning: Taxonomies, applications, and challenges","volume":"27","author":"Alsharif","year":"2024","journal-title":"Internet Things"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Jin, Y., Zhu, H., Xu, J., and Chen, Y. (2023). Federated Learning: Fundamentals and Advances, Springer.","DOI":"10.1007\/978-981-19-7083-2"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1622","DOI":"10.1109\/COMST.2021.3075439","article-title":"Federated Learning for Internet of Things: A Comprehensive Survey","volume":"23","author":"Nguyen","year":"2021","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1109\/MWC.014.2300319","article-title":"Split Learning in 6G Edge Networks","volume":"31","author":"Lin","year":"2024","journal-title":"IEEE Wirel. Commun."},{"key":"ref_29","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":"ref_30","unstructured":"Ludwig, H., and Baracaldo, N. (2022). Split Learning: A Resource Efficient Model and Data Parallel Approach for Distributed Deep Learning. Federated Learning: A Comprehensive Overview of Methods and Applications, Springer International Publishing."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Turina, V., Zhang, Z., Esposito, F., and Matta, I. (2021, January 5\u201310). Federated or Split? A Performance and Privacy Analysis of Hybrid Split and Federated Learning Architectures. Proceedings of the 2021 IEEE 14th International Conference on Cloud Computing (CLOUD), Chicago, IL, USA.","DOI":"10.1109\/CLOUD53861.2021.00038"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"100436","DOI":"10.1016\/j.simpa.2022.100436","article-title":"Federated split GANs for collaborative training with heterogeneous devices","volume":"14","author":"Liang","year":"2022","journal-title":"Softw. Impacts"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Naseh, D., Abdollahpour, M., and Tarchi, D. (2024). Real-World Implementation and Performance Analysis of Distributed Learning Frameworks for 6G IoT Applications. Information, 15.","DOI":"10.3390\/info15040190"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"122807","DOI":"10.1016\/j.eswa.2023.122807","article-title":"A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations","volume":"242","author":"Zhao","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Naseh, D., Shinde, S.S., and Tarchi, D. (2024, January 3\u20136). Multi-Layer Distributed Learning for Intelligent Transportation Systems in 6G Aerial-Ground Integrated Networks. Proceedings of the 2024 Joint European Conference on Networks and Communications & 6G Summit (EuCNC\/6G Summit), Antwerp, Belgium.","DOI":"10.1109\/EuCNC\/6GSummit60053.2024.10597130"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Naseh, D., Shinde, S.S., and Tarchi, D. (2024, January 5\u20138). Distributed Learning Framework for Earth Observation on Multilayer Non-Terrestrial Networks. Proceedings of the 2024 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN), Stockholm, Sweden.","DOI":"10.1109\/ICMLCN59089.2024.10625007"},{"key":"ref_37","unstructured":"Price, E. (2025). Federated Learning for Privacy-Preserving Edge Intelligence: A Scalable Systems Perspective. J. Comput. Sci. Softw. Appl., 5."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Jia, Y., Liu, B., Zhang, X., Dai, F., Khan, A., Qi, L., and Dou, W. (2024). Model Pruning-enabled Federated Split Learning for Resource-constrained Devices in Artificial Intelligence Empowered Edge Computing Environment. ACM Trans. Sens. Netw.","DOI":"10.1145\/3687478"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A Comprehensive Survey on Transfer Learning","volume":"109","author":"Zhuang","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"142","DOI":"10.23919\/ICN.2020.0009","article-title":"Space-air-ground integrated vehicular network for connected and automated vehicles: Challenges and solutions","volume":"1","author":"Niu","year":"2020","journal-title":"Intell. Converg. Netw."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Naseh, D., Shinde, S.S., Tarchi, D., and DeCola, T. (2024, January 8\u201311). Distributed Intelligent Framework for Remote Area Observation on Multilayer Non-Terrestrial Networks. Proceedings of the 2024 IEEE International Mediterranean Conference on Communications and Networking (MeditCom), Madrid, Spain.","DOI":"10.1109\/MeditCom61057.2024.10621222"},{"key":"ref_42","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon, Y., Michael, K., Fang, J., Yifu, Z., Wong, C., and Montes, D. (2022). ultralytics\/yolov5: V7.0\u2014YOLOv5 SOTA Realtime Instance Segmentation (v7.0). Zenodo."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016, January 27\u201330). The Cityscapes Dataset for Semantic Urban Scene Understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref_44","unstructured":"Khanam, R., and Hussain, M. (2024). What is YOLOv5: A deep look into the internal features of the popular object detector. arXiv."},{"key":"ref_45","first-page":"100857","article-title":"Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning","volume":"38","author":"Desislavov","year":"2023","journal-title":"Sustain. Comput. Inform. Syst."}],"container-title":["Network"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2673-8732\/5\/3\/41\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:47:20Z","timestamp":1760035640000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2673-8732\/5\/3\/41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":45,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["network5030041"],"URL":"https:\/\/doi.org\/10.3390\/network5030041","relation":{},"ISSN":["2673-8732"],"issn-type":[{"value":"2673-8732","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]}}}