ELTFL: A Trusted Heterogeneous Federated Learning in Edge Scenario
Tsinghua Science and Technology · 2026-10 · 31 (5) · 2449-2467
DOI: 10.26599/tst.2024.9010264 ↗Kurz gefasst
Fachartikel in der Zeitschrift Tsinghua Science and Technology, 2026-10. Verfasst von Jinshan Lai und 3 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben.
Abstract (Originalsprache)
Federated learning (FL) enables deployment of smart applications, where the intelligent model is trained with distributed data to achieve high accuracy and generalization capabilities. However, resource-constrained terminal devices are unable to train a global model at scale, leading to device dropouts and reduced data utilization. To achieve effective FL among heterogeneous models, we propose the edge learning based trusted heterogeneous federated learning scheme (ELTFL), which allows clients with different heterogeneous models to participate in FL through the application of knowledge distillation (KD). Specifically, ELTFL utilizes integrated distillation to build a heterogeneous multi-model training architecture for FL, which downloads global models to edge servers while preserving heterogeneous models of terminal devices. The edge server utilizes a small set of datasets along with probabilistic outputs from terminal devices to train the global model, and performs global model aggregation in the cloud. In addition, to safeguard against gradient leakage attacks, we introduce a lightweight iterative masking technique between edge servers and terminal devices to ensure the privacy and reliability of intermediate information. Extensive experiments on the CIFAR10 and CIFAR100 datasets demonstrate that ELTFL performs well in terms of accuracy, robustness to data heterogeneity, communication overhead, and privacy protection.
Zitieren
APA
Lai, J., Wang, R., Luo, C., & Zhang, F. (2026). ELTFL: A Trusted Heterogeneous Federated Learning in Edge Scenario. Tsinghua Science and Technology, 31(5), 2449-2467. https://doi.org/10.26599/tst.2024.9010264
Vancouver
Lai J, Wang R, Luo C, Zhang F. ELTFL: A Trusted Heterogeneous Federated Learning in Edge Scenario. Tsinghua Science and Technology. 2026;31(5):2449-2467. doi:10.26599/tst.2024.9010264
BibTeX
@article{Lai2026,
author = {Lai, Jinshan and Wang, Ruijin and Luo, Chuanwen and Zhang, Fengli},
title = {ELTFL: A Trusted Heterogeneous Federated Learning in Edge Scenario},
journal = {Tsinghua Science and Technology},
year = {2026},
volume = {31},
number = {5},
pages = {2449--2467},
doi = {10.26599/tst.2024.9010264}
}
EUVIMED