Learn to Adapt to New Environments From Past Experience and Few Pilot Blocks
IEEE Transactions on Cognitive Communications and Networking · 2023-04 · 9 (2) · 373-385
DOI: 10.1109/tccn.2022.3228536 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2023-04. Verfasst von Ouya Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Imperial College London.
Abstract (Originalsprache)
In recent years, deep learning has been widely applied in communications and achieved remarkable performance improvement. Most of the existing works are based on data-driven deep learning, which requires a significant amount of training data for the communication model to adapt to new environments and results in huge computing resources for collecting data and retraining the model. In this paper, we will significantly reduce the required amount of training data for new environments by leveraging the learning experience from the known environments. Therefore, we introduce few-shot learning to enable the communication model to generalize to new environments, which is realized by an attention-based method. With the attention network embedded into the deep learning-based communication model, environments with different power delay profiles can be learnt together in the training process, which is called the learning experience. By exploiting the learning experience, the communication model only requires few pilot blocks to perform well in the new environment. Through an example of deep-learning-based channel estimation, we demonstrate that this novel design method achieves better performance than the existing data-driven approach designed for few-shot learning.
Förderung
- Imperial College London
Zitieren
APA
Wang, O., Gao, J., & Li, G. Y. (2023). Learn to Adapt to New Environments From Past Experience and Few Pilot Blocks. IEEE Transactions on Cognitive Communications and Networking, 9(2), 373-385. https://doi.org/10.1109/tccn.2022.3228536
Vancouver
Wang O, Gao J, Li GY. Learn to Adapt to New Environments From Past Experience and Few Pilot Blocks. IEEE Transactions on Cognitive Communications and Networking. 2023;9(2):373-385. doi:10.1109/tccn.2022.3228536
BibTeX
@article{Wang2023,
author = {Wang, Ouya and Gao, Jiabao and Li, Geoffrey Ye},
title = {Learn to Adapt to New Environments From Past Experience and Few Pilot Blocks},
journal = {IEEE Transactions on Cognitive Communications and Networking},
year = {2023},
volume = {9},
number = {2},
pages = {373--385},
doi = {10.1109/tccn.2022.3228536}
}
EUVIMED