Journal article · 2026 · Open access
Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning
IEEE Transactions on Mobile Computing, 25(12), 22820–22834 · Published 20 August 2026 · DOI 10.1109/tmc.2026.3725778
In brief
“Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning” is a 2026 journal article by Xiao Jiang and 3 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
- 39
- Authors
- 4
Abstract
Federated unlearning (FU) has become a critical capability of privacy-sensitive edge intelligence, which enables mobile and Internet of Things (IoT) devices to revoke previously contributing data from collaboratively trained models. While previous studies have explored unlearning via retraining or approximate mechanisms, most have assumed idealized homogeneous data distributions in federated learning (FL). This caused them to overlook the substantial impact of data heterogeneity, which is a fundamental challenge in federated edge networks. To address this limitation, we propose an adaptive federated unlearning framework tailored for heterogeneous edge environments. Through a representation-level analysis, we characterize how data heterogeneity shapes forgetting behaviors and identify two key factors that hinder unlearning performance: directed representation drift and heterogeneity-induced hard samples. Guided by these insights, we develop contrastive federated unlearning (CFU), a two-stage framework that integrates local contrastive fine-tuning with global model calibration. CFU employs contrastive unlearning to induce targeted representation shifts, whereas lightweight fine-tuning mitigates the adverse effects of heterogeneity. The unlearning process is further safeguarded through localized forgetting and data-free knowledge distillation. Extensive experiments on both client and sample-level unlearning tasks demonstrate that CFU consistently outperforms state-ofthe- art approximate unlearning methods across diverse realworld datasets, achieving a 2-4× efficiency improvement over retraining.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Jiang, X., Zhong, H., Chen, D., & Cui, J. (2026). Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning. IEEE Transactions on Mobile Computing, 25(12), 22820–22834. https://doi.org/10.1109/tmc.2026.3725778
MLA 9
Jiang, Xiao, et al. “Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning.” IEEE Transactions on Mobile Computing, vol. 25, no. 12, 2026, pp. 22820–22834. https://doi.org/10.1109/tmc.2026.3725778.
Chicago
Jiang, Xiao, Hong Zhong, Depeng Chen, and Jie Cui. 2026. “Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning.” IEEE Transactions on Mobile Computing 25 (12): 22820–22834. https://doi.org/10.1109/tmc.2026.3725778.
Harvard
Jiang, X. et al. (2026) ‘Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning’, IEEE Transactions on Mobile Computing, 25(12), pp. 22820–22834. doi:10.1109/tmc.2026.3725778.
IEEE
X. Jiang, H. Zhong, D. Chen, and J. Cui, “Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning,” IEEE Transactions on Mobile Computing, vol. 25, no. 12, pp. 22820–22834, 2026, doi: 10.1109/tmc.2026.3725778.
BibTeX
@article{jiang2026adaptive,
title = {{Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning}},
author = {Jiang, Xiao and Zhong, Hong and Chen, Depeng and Cui, Jie},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {12},
pages = {22820--22834},
doi = {10.1109/tmc.2026.3725778},
url = {https://doi.org/10.1109/tmc.2026.3725778}
}
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 unlearning
- data heterogeneity
- edge networks
- contrastive learning
- fine-tuning
- representational drift
- forgetting
- data-free knowledge distillation
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?
Jiang, X., Zhong, H., Chen, D., & Cui, J. (2026). Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning. IEEE Transactions on Mobile Computing, 25(12), 22820–22834. https://doi.org/10.1109/tmc.2026.3725778
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?
Xiao Jiang, Hong Zhong, Depeng Chen, Jie Cui.
What is the DOI of this paper?
10.1109/tmc.2026.3725778, permanently at https://doi.org/10.1109/tmc.2026.3725778. 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.