EUVIMEDEUVIMED entdecken
Crossref

Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning

Xiao Jiang, Hong Zhong, Depeng Chen, Jie Cui

IEEE Transactions on Mobile Computing · 2026-12 · 25 (12) · 22820-22834

DOI: 10.1109/tmc.2026.3725778 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-12. Verfasst von Xiao Jiang und 3 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Anhui Province, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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-of-the-art approximate unlearning methods across diverse real-world datasets, achieving a 2–4× efficiency improvement over retraining.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Anhui Province, China

Zitieren

APA

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

Vancouver

Jiang X, Zhong H, Chen D, Cui J. Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning. IEEE Transactions on Mobile Computing. 2026;25(12):22820-22834. doi:10.1109/tmc.2026.3725778

BibTeX
@article{Jiang2026,
  author = {Jiang, Xiao and Zhong, Hong and Chen, Depeng and Cui, Jie},
  title = {Adaptive Federated Unlearning in Heterogeneous Edge Networks via Contrastive Fine-Tuning},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {12},
  pages = {22820--22834},
  doi = {10.1109/tmc.2026.3725778}
}
Kostenlos starten →