Journal article · 2026 · Open access

Accelerating Federated Learning Under Client Dropout via Joint Bandwidth Allocation and Prototype Fine-Tuning in Mobile Edge Computing Networks

Jian Tang, Luxi Cheng, Xiuhua Li, Xiaofei Wang, Derrick Wing Kwan Ng, Victor C. M. Leung

IEEE Transactions on Mobile Computing, 25(11), 20443–20460 · Published 13 July 2026 · DOI 10.1109/tmc.2026.3712349

Open full textCite this paper

In brief

“Accelerating Federated Learning Under Client Dropout via Joint Bandwidth Allocation and Prototype Fine-Tuning in Mobile Edge Computing Networks” is a 2026 journal article by Jian Tang and 5 co-authors, published in IEEE Transactions on Mobile Computing. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Mobile Computing.

Citations
0
References
57
Authors
6

Abstract

Deploying federated learning (FL) in mobile edge computing (MEC) networks enables collaborative model training while preserving the privacy of raw data. However, due to system heterogeneity, statistical heterogeneity of mobile clients (MCs), and client dropout, optimizing bandwidth allocation and fine-tuning the global model is essential for accelerating FL. We formulate a problem to reduce the sum of waiting time of the MCs and edge server (ES), which can indirectly accelerate the FL process, and decompose it into two subproblems. We then propose a joint bandwidth allocation and prototype fine-tuning (BAPFT) framework to address them. In each round, BAPFT dynamically allocates bandwidth to the participating MCs, determines a deadline, thereby reducing the waiting time of the MCs and ES caused by system heterogeneity under client dropout. Moreover, BAPFT adopts mixup prototypes maintained at the ES to fine-tune the global model, which mitigates the negative impact of missing updates from the dropped MCs and statistical heterogeneity. Extensive experiments on three datasets demonstrate that BAPFT significantly reduces model training latency by an average of 16.78% and rounds by an average of 5.72% compared to baseline frameworks.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Tang, J., Cheng, L., Li, X., Wang, X., Ng, D. W. K., & Leung, V. C. M. (2026). Accelerating Federated Learning Under Client Dropout via Joint Bandwidth Allocation and Prototype Fine-Tuning in Mobile Edge Computing Networks. IEEE Transactions on Mobile Computing, 25(11), 20443–20460. https://doi.org/10.1109/tmc.2026.3712349

MLA 9

Tang, Jian, et al. “Accelerating Federated Learning Under Client Dropout via Joint Bandwidth Allocation and Prototype Fine-Tuning in Mobile Edge Computing Networks.” IEEE Transactions on Mobile Computing, vol. 25, no. 11, 2026, pp. 20443–20460. https://doi.org/10.1109/tmc.2026.3712349.

Chicago

Tang, Jian, Luxi Cheng, Xiuhua Li, Xiaofei Wang, Derrick Wing Kwan Ng, and Victor C. M. Leung. 2026. “Accelerating Federated Learning Under Client Dropout via Joint Bandwidth Allocation and Prototype Fine-Tuning in Mobile Edge Computing Networks.” IEEE Transactions on Mobile Computing 25 (11): 20443–20460. https://doi.org/10.1109/tmc.2026.3712349.

Harvard

Tang, J. et al. (2026) ‘Accelerating Federated Learning Under Client Dropout via Joint Bandwidth Allocation and Prototype Fine-Tuning in Mobile Edge Computing Networks’, IEEE Transactions on Mobile Computing, 25(11), pp. 20443–20460. doi:10.1109/tmc.2026.3712349.

IEEE

J. Tang, L. Cheng, X. Li, X. Wang, D. W. K. Ng, and V. C. M. Leung, “Accelerating Federated Learning Under Client Dropout via Joint Bandwidth Allocation and Prototype Fine-Tuning in Mobile Edge Computing Networks,” IEEE Transactions on Mobile Computing, vol. 25, no. 11, pp. 20443–20460, 2026, doi: 10.1109/tmc.2026.3712349.

BibTeX

@article{tang2026accelerating,
  title     = {{Accelerating Federated Learning Under Client Dropout via Joint Bandwidth Allocation and Prototype Fine-Tuning in Mobile Edge Computing Networks}},
  author    = {Tang, Jian and Cheng, Luxi and Li, Xiuhua and Wang, Xiaofei and Ng, Derrick Wing Kwan and Leung, Victor C. M.},
  journal   = {IEEE Transactions on Mobile Computing},
  year      = {2026},
  volume    = {25},
  number    = {11},
  pages     = {20443--20460},
  doi       = {10.1109/tmc.2026.3712349},
  url       = {https://doi.org/10.1109/tmc.2026.3712349}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • federated learning
  • mobile edge computing
  • client dropout
  • bandwidth allocation
  • statistical heterogeneity
  • waiting time minimization
  • deadline scheduling
  • edge servers

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Tang, J., Cheng, L., Li, X., Wang, X., Ng, D. W. K., & Leung, V. C. M. (2026). Accelerating Federated Learning Under Client Dropout via Joint Bandwidth Allocation and Prototype Fine-Tuning in Mobile Edge Computing Networks. IEEE Transactions on Mobile Computing, 25(11), 20443–20460. https://doi.org/10.1109/tmc.2026.3712349

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE Transactions on Mobile Computing: sign in and open the full text from this page.

Who wrote this paper?

Jian Tang, Luxi Cheng, Xiuhua Li, Xiaofei Wang, Derrick Wing Kwan Ng, Victor C. M. Leung.

What is the DOI of this paper?

10.1109/tmc.2026.3712349, permanently at https://doi.org/10.1109/tmc.2026.3712349. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.