Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty
IEEE Transactions on Mobile Computing · 2026 · 1-14
DOI: 10.1109/tmc.2026.3751775 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026. Verfasst von Ziruo Hao und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Zitieren
APA
Hao, Z., Cui, Z., Yang, T., Fang, Y., Wu, X., Feng, H., & Hu, B. (2026). Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty. IEEE Transactions on Mobile Computing, 1-14. https://doi.org/10.1109/tmc.2026.3751775
Vancouver
Hao Z, Cui Z, Yang T, Fang Y, Wu X, Feng H, et al. Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty. IEEE Transactions on Mobile Computing. 2026:1-14. doi:10.1109/tmc.2026.3751775
BibTeX
@article{Hao2026,
author = {Hao, Ziruo and Cui, Zhenhua and Yang, Tao and Fang, Yunjie and Wu, Xiaofeng and Feng, Hui and Hu, Bo},
title = {Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
pages = {1--14},
doi = {10.1109/tmc.2026.3751775}
}
EUVIMED