EUVIMEDEUVIMED entdecken
Crossref

pFedLoRA: Model-Heterogeneous Personalized Federated Learning With Homogeneous Low-Rank Adapter Sharing on Mobile Edge Devices

Liping Yi, Heng Zhang, Han Yu, Gang Wang, Xiaoguang Liu, Qinghua Hu

IEEE Transactions on Mobile Computing · 2026-09 · 25 (9) · 13898-13911

DOI: 10.1109/tmc.2026.3674996 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-09. Verfasst von Liping Yi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Ministry of Education - Singapore, Academic Research Fund Tier 1.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) is an emerging machine learning paradigm in which a central server coordinates multiple participants (FL clients) collaboratively to train on decentralized data. In practice, FL often faces data, system, and model heterogeneity, which inspires the field of Model-Heterogeneous Personalized Federated Learning (MHPFL). However, existing MHPFL methods rely on extra public data or ignore the relationship between local private heterogeneous models and shared homogeneous models across clients. This leads to unsatisfactory model performance, computational overheads, and communication costs. To bridge this gap, we propose a novel and efficient model-heterogeneous p ersonalized Fed erated learning framework ( pFedLoRA ) based on sharing homogeneous Low-Rank Adapter ( LoRA ) which is popular for fine-tuning pre-trained models. Specifically, we devise a lightweight homogeneous adapter, rather than apply the typical LoRA, to facilitate each client’s heterogeneous local model training with our proposed iterative training for global-local bidirectional knowledge exchange. The homogeneous small local adapters are aggregated on the FL server to generate a global adapter. We theoretically prove its $\mathcal {O}(1/T)$ O ( 1 / T ) non-convex convergence rate. Experiments on 5 datasets demonstrate pFedLoRA outperforms 9 state-of-the-art baselines in model accuracy with $11.81 \times$ 11 . 81 × computation and $7.41\times$ 7 . 41 × communication cost saving.

Förderung

  • National Natural Science Foundation of China
  • Ministry of Education - Singapore
  • Academic Research Fund Tier 1

Zitieren

APA

Yi, L., Zhang, H., Yu, H., Wang, G., Liu, X., & Hu, Q. (2026). pFedLoRA: Model-Heterogeneous Personalized Federated Learning With Homogeneous Low-Rank Adapter Sharing on Mobile Edge Devices. IEEE Transactions on Mobile Computing, 25(9), 13898-13911. https://doi.org/10.1109/tmc.2026.3674996

Vancouver

Yi L, Zhang H, Yu H, Wang G, Liu X, Hu Q. pFedLoRA: Model-Heterogeneous Personalized Federated Learning With Homogeneous Low-Rank Adapter Sharing on Mobile Edge Devices. IEEE Transactions on Mobile Computing. 2026;25(9):13898-13911. doi:10.1109/tmc.2026.3674996

BibTeX
@article{Yi2026,
  author = {Yi, Liping and Zhang, Heng and Yu, Han and Wang, Gang and Liu, Xiaoguang and Hu, Qinghua},
  title = {pFedLoRA: Model-Heterogeneous Personalized Federated Learning With Homogeneous Low-Rank Adapter Sharing on Mobile Edge Devices},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {9},
  pages = {13898--13911},
  doi = {10.1109/tmc.2026.3674996}
}
Kostenlos starten →