Federated Split Learning with Large Language Models Integration: A Study on Potential Container Source Identification in Sea-Rail Intermodal Transport
INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL · 26.05.2026 · 21 (3)
DOI: 10.15837/ijccc.2026.3.7263 ↗Kurz gefasst
Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, online erschienen am 26.05.2026. Verfasst von Weiguang Ma und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Ma, W., Huang, L., Zhang, Q., Wang, Y., Zhang, X., & Song, R. (2026). Federated Split Learning with Large Language Models Integration: A Study on Potential Container Source Identification in Sea-Rail Intermodal Transport. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 21(3). https://doi.org/10.15837/ijccc.2026.3.7263
Vancouver
Ma W, Huang L, Zhang Q, Wang Y, Zhang X, Song R. Federated Split Learning with Large Language Models Integration: A Study on Potential Container Source Identification in Sea-Rail Intermodal Transport. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL. 2026;21(3). doi:10.15837/ijccc.2026.3.7263
BibTeX
@article{Ma2026,
author = {Ma, Weiguang and Huang, Lei and Zhang, Qianyao and Wang, Ying and Zhang, Xiong and Song, Rongjia},
title = {Federated Split Learning with Large Language Models Integration: A Study on Potential Container Source Identification in Sea-Rail Intermodal Transport},
journal = {INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL},
year = {2026},
volume = {21},
number = {3},
doi = {10.15837/ijccc.2026.3.7263}
}
EUVIMED