SemFedVAE: A Communication-Efficient Federated Learning Framework for Variational Autoencoder With Semantic Latent Space Alignment
IEEE Transactions on Mobile Computing · 2026 · 1-16
DOI: 10.1109/tmc.2026.3755564 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026. Verfasst von Jincheng Cai und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Zitieren
APA
Cai, J., Zhao, Q., Li, J., Feng, L., Chen, X., Zhu, J., & Zhao, N. (2026). SemFedVAE: A Communication-Efficient Federated Learning Framework for Variational Autoencoder With Semantic Latent Space Alignment. IEEE Transactions on Mobile Computing, 1-16. https://doi.org/10.1109/tmc.2026.3755564
Vancouver
Cai J, Zhao Q, Li J, Feng L, Chen X, Zhu J, et al. SemFedVAE: A Communication-Efficient Federated Learning Framework for Variational Autoencoder With Semantic Latent Space Alignment. IEEE Transactions on Mobile Computing. 2026:1-16. doi:10.1109/tmc.2026.3755564
BibTeX
@article{Cai2026,
author = {Cai, Jincheng and Zhao, Qinglin and Li, Jian and Feng, Li and Chen, Xu and Zhu, Jian and Zhao, Ni},
title = {SemFedVAE: A Communication-Efficient Federated Learning Framework for Variational Autoencoder With Semantic Latent Space Alignment},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
pages = {1--16},
doi = {10.1109/tmc.2026.3755564}
}
EUVIMED