EUVIMEDEUVIMED entdecken
Crossref

FedME 2 : Memory Evaluation & Erase Promoting Federated Unlearning in DTMN

Hui Xia, Shuo Xu, Jiaming Pei, Rui Zhang, Zhi Yu, Weitao Zou, Lukun Wang, Chao Liu

IEEE Journal on Selected Areas in Communications · 2023-11 · 41 (11) · 3573-3588

DOI: 10.1109/jsac.2023.3310049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Communications, 2023-11. Verfasst von Hui Xia und 7 weiteren Autor:innen. Die Arbeit wurde bisher 64-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Startup Research Foundation for Distinguished Scholars.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Digital Twins (DTs) can generate digital replicas for mobile networks (MNs) that accurately reflect the state of MN. Machine learning (ML) models trained in DT for MN (DTMN) virtual environments can be more robustly implemented in MN. This can avoid the training difficulties and runtime errors caused by MN instability and multiple failures. However, when using data from various devices in the MN system, DTs must prioritize data privacy. Federated learning (FL) enables the construction of models without data leaving devices to protect DTMN data privacy. Nevertheless, FL’s privacy protection needs further improvement for it only guarantees device-level data ownership but ignores that models may retain private information from data. Therefore, this paper focuses on data forgetting in privacy protection, and proposes a novel FL-based unlearning framework (FedME2), which contains MEval and MErase modules. Guided by memory evaluation information from MEval and employing MErase’s multi-loss training approach, FedME2 gets accurate data forgetting in DTMN. In four DTMN virtual environments, FedME2 achieves an average data forgetting rate of approximately 75% for global models under FL and kept the influence on global models’ accuracy below 4%. FedME2 has better data forgetting and improves DTMN data privacy protection while guaranteeing model accuracy.

Förderung

  • National Natural Science Foundation of China
  • Startup Research Foundation for Distinguished Scholars

Zitieren

APA

Xia, H., Xu, S., Pei, J., Zhang, R., Yu, Z., Zou, W., Wang, L., & Liu, C. (2023). FedME 2 : Memory Evaluation & Erase Promoting Federated Unlearning in DTMN. IEEE Journal on Selected Areas in Communications, 41(11), 3573-3588. https://doi.org/10.1109/jsac.2023.3310049

Vancouver

Xia H, Xu S, Pei J, Zhang R, Yu Z, Zou W, et al. FedME 2 : Memory Evaluation & Erase Promoting Federated Unlearning in DTMN. IEEE Journal on Selected Areas in Communications. 2023;41(11):3573-3588. doi:10.1109/jsac.2023.3310049

BibTeX
@article{Xia2023,
  author = {Xia, Hui and Xu, Shuo and Pei, Jiaming and Zhang, Rui and Yu, Zhi and Zou, Weitao and Wang, Lukun and Liu, Chao},
  title = {FedME 2 : Memory Evaluation & Erase Promoting Federated Unlearning in DTMN},
  journal = {IEEE Journal on Selected Areas in Communications},
  year = {2023},
  volume = {41},
  number = {11},
  pages = {3573--3588},
  doi = {10.1109/jsac.2023.3310049}
}
Kostenlos starten →