Journal article · 2026 · Open access
Fed-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
IEEE Transactions on Mobile Computing, 25(11), 20278–20295 · Published 8 July 2026 · DOI 10.1109/tmc.2026.3711494
In brief
“Fed-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices” is a 2026 journal article by Changyu Li and 7 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
- 63
- Authors
- 8
Abstract
Federated fine-tuning provides a practical route to adapt large language models (LLMs) on edge devices without centralizing private data. However, in mobile deployments, the training wall-clock is often dominated by straggler-limited uplink communication under heterogeneous bandwidth, intermittent participation, and non-IID client data. Although parameter-efficient fine-tuning (PEFT) methods such as LoRA and QLoRA reduce local memory and trainable parameters, repeated transmission of adapter updates remains a major bottleneck. We propose Fed-FSTQ, a semantic-sensitivity-aware communication-control primitive for communication-efficient federated LLM fine-tuning. Fed-FSTQ uses a lightweight token-level Fisher proxy to estimate semantic sensitivity, couples token-guided sparsification with mixed-precision adapter-update quantization, and allocates higher communication fidelity to semantically load-bearing evidence while suppressing redundant transmission. The method is drop-in compatible with standard federated PEFT pipelines and requires no change to the server aggregation rule. Experiments on multilingual QA and medical QA under non-IID partitions show that Fed-FSTQ reduces cumulative uplink traffic required to reach a fixed quality threshold by46×relative to a Fed-LoRA baseline and improves straggler-limited wall-clock time-to-accuracy by52%. Under the corrected Controlled LTE-20Mbps accounting, Fed-FSTQ reduces per-round time from 414.60s to 67.29s and reduces per-round energy from 839.20J to 146.28J, yielding a6.16×speedup. On NVIDIA Jetson-class edge devices, Fisher-guided token reduction also yields up to a1.55×inference speedup, demonstrating deployability under tight resource constraints.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Li, C., Huang, S., Liu, J., Lei, M., Xing, J., Wu, K., Wang, L., & Luo, F. (2026). Fed-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices. IEEE Transactions on Mobile Computing, 25(11), 20278–20295. https://doi.org/10.1109/tmc.2026.3711494
MLA 9
Li, Changyu, et al. “Fed-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices.” IEEE Transactions on Mobile Computing, vol. 25, no. 11, 2026, pp. 20278–20295. https://doi.org/10.1109/tmc.2026.3711494.
Chicago
Li, Changyu, Shuanghong Huang, Jiashen Liu, Ming Lei, Jidu Xing, Kaishun Wu, Lu Wang, and Fei Luo. 2026. “Fed-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices.” IEEE Transactions on Mobile Computing 25 (11): 20278–20295. https://doi.org/10.1109/tmc.2026.3711494.
Harvard
Li, C. et al. (2026) ‘Fed-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices’, IEEE Transactions on Mobile Computing, 25(11), pp. 20278–20295. doi:10.1109/tmc.2026.3711494.
IEEE
C. Li et al., “Fed-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices,” IEEE Transactions on Mobile Computing, vol. 25, no. 11, pp. 20278–20295, 2026, doi: 10.1109/tmc.2026.3711494.
BibTeX
@article{li2026fstq,
title = {{Fed-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices}},
author = {Li, Changyu and Huang, Shuanghong and Liu, Jiashen and Lei, Ming and Xing, Jidu and Wu, Kaishun and Wang, Lu and Luo, Fei},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {11},
pages = {20278--20295},
doi = {10.1109/tmc.2026.3711494},
url = {https://doi.org/10.1109/tmc.2026.3711494}
}
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 fine-tuning
- large language models
- edge devices
- communication efficiency
- parameter-efficient fine-tuning
- LoRa
- QLoRA
- mixed-precision quantization
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Li, C., Huang, S., Liu, J., Lei, M., Xing, J., Wu, K., Wang, L., & Luo, F. (2026). Fed-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices. IEEE Transactions on Mobile Computing, 25(11), 20278–20295. https://doi.org/10.1109/tmc.2026.3711494
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?
Changyu Li, Shuanghong Huang, Jiashen Liu, Ming Lei, Jidu Xing, Kaishun Wu, Lu Wang, Fei Luo.
What is the DOI of this paper?
10.1109/tmc.2026.3711494, permanently at https://doi.org/10.1109/tmc.2026.3711494. 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.