Federated Split Learning with Large Language Models Integration: A Study on Potential Container Source Identification in Sea-Rail Intermodal Transport
DOI:
https://doi.org/10.15837/ijccc.2026.3.7263Keywords:
federated learning, segmentation learning, large language model, sea-rail intermodal transport, privacy protectionAbstract
To address the challenge of potential container source identification in sea-rail intermodal transport scenarios, which arises from data silos and privacy barriers among multiple stakeholders, this paper proposes FSL-Qwen, a Federated Split Learning framework integrated with Large Language Models. Innovative to this framework is the vertical partitioning of the Qwen model at the embedding layer: clients (e.g., ports, railways, customs) deploy only lightweight embedding layers for local feature extraction, while the server retains the Transformer backbone for centralized reasoning. This architecture decouples local computation from inference, theoretically reducing client-side complexity to O(1) and drastically minimizing communication overhead compared to standard Federated Learning. To resolve cross-domain semantic heterogeneity, a ChatML-based semantic alignment mechanism is introduced, enabling collaborative inference without sharing raw records. Privacy analysis demonstrates that the framework achieves inherent structural isolation, converting data reconstruction attacks into blind inverse problems. Experiments on a dataset of 48,800 SRIT container data confirm that FSL-Qwen achieves a predictive accuracy of 94.0% and an F1-score of 94.1%, effectively matching the centralized upper bound while limiting client-side memory usage to merely 0.26 GB. These results validate FSL-Qwen as a robust, efficient, and privacy-preserving paradigm for intelligent logistics decision-making.
References
Luo, Y. (2024). Paradigm shift and theoretical implications for the era of global disorder, Journal of International Business Studies, 55(2), 127-135, 2024. https://doi.org/10.1057/s41267-023-00659-2
McKibbin, W.; Fernando, R. (2023). The global economic impacts of the COVID-19 pandemic, Economic Modelling, 129, 106551, 2023. https://doi.org/10.1016/j.econmod.2023.106551
Liu, W.; Wang, L.; Yan, B.; Zhu, X.; Liu, Z. (2025). Integrated optimization of dynamic deployment and scheduling for rail-mounted gantry cranes in sea-rail intermodal port with on-dock rails, Transportation Research Part E: Logistics and Transportation Review, 202, 104312, 2025. https://doi.org/10.1016/j.tre.2025.104312
Shenoy, D.; Bhat, R., ; Krishna Prakasha, K. (2025). Exploring privacy mechanisms and metrics in federated learning, Artificial Intelligence Review, 58(8), 223, 2025. https://doi.org/10.1007/s10462-025-11170-5
Wang, Y.; Wu, Y.; Hao, C.; Hong, C. (2025). Research on the scheduling in sea-rail intermodal trains based on full-length and full-occupied strategy, Research in Transportation Business & Management, 59, 101301, 2025. https://doi.org/10.1016/j.rtbm.2025.101301
Feng, C.; Lei, Y. (2024). Research on interval prediction method of railway freight based on big data and TCN-BiLSTM-QR, IET Intelligent Transport Systems, 18(12), 2713-2724, 2024. https://doi.org/10.1049/itr2.12531
Montoya, G.; Lozano-Garzón, C.; Paternina-Arboleda, C.; Donoso, Y. (2025). A Mathematical Optimization Approach for Prioritized Services in IoT Networks for Energy-constrained Smart Cities, International Journal of Computers Communications & Control, 20(1). https://doi.org/10.15837/ijccc.2025.1.6912
Zhang, X.; Mavromatis, A.; Vafeas, A.; Nejabati, R.; Simeonidou, D. (2023). Federated feature selection for horizontal federated learning in IoT networks, IEEE Internet of Things Journal, 10(11), 10095-10112, 2023. https://doi.org/10.1109/JIOT.2023.3237032
Gulati, S.; Guleria, K.; Goyal, N.; Alzubi, A. A.; Castilla, A. K. (2024). A privacy-preserving collaborative federated learning framework for detecting retinal diseases, IEEE Access, 12, 170176- 170203, 2024. https://doi.org/10.1109/ACCESS.2024.3493946
Gong, M.; Zhang, Y.; Gao, Y.; Qin, A. K.; Wu, Y.; Wang, S.; Zhang, Y. (2023). A multi-modal vertical federated learning framework based on homomorphic encryption, IEEE Transactions on Information Forensics and Security, 19, 1826-1839, 2023. https://doi.org/10.1109/TIFS.2023.3340994
Vepakomma, P.; Gupta, O.; Swedish, T.; Raskar, R. (2018). Split learning for health: Distributed deep learning without sharing raw patient data, arXiv preprint, arXiv:1812.00564, 2018.
Xue, R.; Xue, K.; Zhu, B.; Luo, X.; Zhang, T.; Sun, Q.; Lu, J. (2023). Differentially private federated learning with an adaptive noise mechanism, IEEE Transactions on Information Forensics and Security, 19, 74-87, 2023. https://doi.org/10.1109/TIFS.2023.3318944
Alqazzaz, A. (2025). Federated Learning with Homomorphic Encryption: A Privacy-Preserving Solution for Smart Cities, International Journal of Computational Intelligence Systems, 18(1), 304, 2025. https://doi.org/10.1007/s44196-025-00829-0
Piccialli, F.; Chiaro, D.; Qi, P.; Bellandi, V.; Damiani, E. (2025). Federated and edge learning for large language models, Information Fusion, 117, 102840, 2025. https://doi.org/10.1016/j.inffus.2024.102840
Zhou, H.; Inkpen, D.; Kantarci, B. (2024). Evaluating and mitigating gender bias in generative large language models, International Journal of Computers Communications & Control, 19(6). https://doi.org/10.15837/ijccc.2024.6.6853
Dantas, P. V.; Cordeiro, L. C.; Junior, W. S. (2025). A review of state-of-the-art techniques for large language model compression, Complex & Intelligent Systems, 11(9), 407, 2025. https://doi.org/10.1007/s40747-025-02019-z
Putrama, I. M.; Martinek, P. (2024). Heterogeneous data integration: Challenges and opportunities, Data in Brief, 56, 110853, 2024. https://doi.org/10.1016/j.dib.2024.110853
Mokhtari, Z.; Amani-Beni, M.; Asgarian, A.; Russo, A.; Qureshi, S.; Karami, A. (2023). Spatial prediction of the urban inter-annual land surface temperature variability: An integrated modeling approach in a rapidly urbanizing semi-arid region, Sustainable Cities and Society, 93, 104523, 2023. https://doi.org/10.1016/j.scs.2023.104523
Peng, T.; Gan, M.; Ou, Q.; Yang, X.; Wei, L.; Rødal Ler, H.; Yu, H. (2024). Railway cold chain freight demand forecasting with graph neural networks: A novel GraphARMA-GRU model, Expert Systems with Applications, 255, 124693, 2024. https://doi.org/10.1016/j.eswa.2024.124693
Liang, X. (2025). Cross-border logistics risk warning system based on federated learning, Scientific reports, 15(1), 39131, 2025. https://doi.org/10.1038/s41598-025-25507-1
Zheng, J.; Chen, Y.; Lai, Q. (2024). PPSFL: Privacy-Preserving Split Federated Learning for heterogeneous data in edge-based Internet of Things, Future Generation Computer Systems, 156, 231-241, 2024. https://doi.org/10.1016/j.future.2024.03.020
Qin, J.; Zhang, X.; Liu, B.; Qian, J. (2023). A split-federated learning and edge-cloud based efficient and privacy-preserving large-scale item recommendation model, Journal of Cloud Computing, 12(1), 57, 2023. https://doi.org/10.1186/s13677-023-00435-5
Li, Y.; Yan, Y.; Tong, Z.; Wang, Y.; Yang, Y.; Bai, M., et al. (2025). Efficient fine-tuning of small-parameter large language models for biomedical bilingual multi-task applications, Applied Soft Computing, 175, 113084, 2025. https://doi.org/10.1016/j.asoc.2025.113084
Huang, L.; Jiang, D.; Zhang, X.; Wang, Y.; Bai, T. (2025). VFed-PU: Identifying Containers with Potential to be Shipped by Rail from Ports with Privacy Protection, Tehnički vjesnik, 32(2), 485-494, 2025. https://doi.org/10.17559/TV-20240601001729
He, Y.; Tan, X.; Ni, J.; Yang, L. T.; Deng, X. (2022). Differentially private set intersection for asymmetrical id alignment, IEEE Transactions on Information Forensics and Security, 17, 3479-3494, 2022. https://doi.org/10.1109/TIFS.2022.3207911
Romanini, D.; Hall, A. J.; Papadopoulos, P.; Titcombe, T.; Ismail, A.; Cebere, T.; Hoeh, M. A. (2021). Pyvertical: A vertical federated learning framework for multi-headed splitnn, arXiv preprint, arXiv:2104.00489, 2021.
Xu, X.; Yang, M.; Yi, W.; Li, Z.; Wang, J.; Hu, H.; Liu, Y. (2024). A stealthy wrongdoer: Featureoriented reconstruction attack against split learning, Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 12130-12139, 2024. https://doi.org/10.1109/CVPR52733.2024.01153
Qiu, Y.; Liu, Y.; Yu, H.; Fang, H.; Chen, B.; Xia, S. T.; Xu, K. (2025). Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization, arXiv preprint, arXiv:2508.20613, 2025.
Zhu, L.; Liu, Z.; Han, S. (2019). Deep leakage from gradients, Advances in neural information processing systems, 32, 2019.
Vepakomma, P.; Swedish, T.; Raskar, R.; Gupta, O.; Dubey, A. (2018). No peek: A survey of private distributed deep learning, arXiv preprint, arXiv:1812.03288, 2018.
Yang, W.; Wang, S.; Wu, D.; Cai, T.; Zhu, Y.; Wei, S.; Li, Y. (2025). Deep learning model inversion attacks and defenses: a comprehensive survey, Artificial Intelligence Review, 58(8), 242, 2025. https://doi.org/10.1007/s10462-025-11248-0
McMahan, B.; Moore, E.; Ramage, D.; Hampson, S.; y Arcas, B. A. (2017). Communicationefficient learning of deep networks from decentralized data, Artificial intelligence and statistics, PMLR 1273-1282, 2017.
Krauth, M.; Ribesmeier, M.; Bešinović, N. (2025). Optimising mode choice in a bi-modal freight network considering sustainability and urban logistic stakeholder perspectives, Transportation Research Interdisciplinary Perspectives, 31, 101442, 2025. https://doi.org/10.1016/j.trip.2025.101442
Additional Files
Published
Issue
Section
License
Copyright (c) 2026 Weiguang Ma, Lei Huang, Qianyao Zhang, Ying Wang, Xiong Zhang, Rongjia Song
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
ONLINE OPEN ACCES: Acces to full text of each article and each issue are allowed for free in respect of Attribution-NonCommercial 4.0 International (CC BY-NC 4.0.
You are free to:
-Share: copy and redistribute the material in any medium or format;
-Adapt: remix, transform, and build upon the material.
The licensor cannot revoke these freedoms as long as you follow the license terms.
DISCLAIMER: The author(s) of each article appearing in International Journal of Computers Communications & Control is/are solely responsible for the content thereof; the publication of an article shall not constitute or be deemed to constitute any representation by the Editors or Agora University Press that the data presented therein are original, correct or sufficient to support the conclusions reached or that the experiment design or methodology is adequate.
