Few-Shot Learning in Wireless Networks: A Meta-Learning Model-Enabled Scheme

Kexin Xiong, Zhongyuan Zhao, Wei Hong, Mugen Peng, Tony Q.S. Quek

研究成果: Conference contribution

3 引文 斯高帕斯(Scopus)

摘要

Restricted by the data sensing capability, it is challenging for a single user to generate high-quality deep learning models based on its collected few-shot data samples. Meta-learning provides a promising paradigm to make full use of historical data at the base stations to improve the performance of few-shot learning tasks. However, it is a dilemma to balance the performance and the communication costs of meta-learning. In this paper, we studied the design of few-shot learning in wireless networks. First, a meta-learning model-based scheme is designed to adapt the few-shot learning tasks, and a multicasting-based model transmission scheme is proposed. Second, a coalition formation-based model selection scheme is designed to achieve a sophisticated tradeoff between the performance and the communication costs of meta-learning. Finally, the simulation results are provided, which show that our proposed scheme can improve the model accuracy performance with low communication costs.

原文English
主出版物標題2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面415-420
頁數6
ISBN(電子)9781665426718
DOIs
出版狀態Published - 2022
事件2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022 - Seoul, Korea, Republic of
持續時間: 2022 5月 162022 5月 20

出版系列

名字2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022

Conference

Conference2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
國家/地區Korea, Republic of
城市Seoul
期間22-05-1622-05-20

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 電腦網路與通信
  • 訊號處理
  • 控制和優化

指紋

深入研究「Few-Shot Learning in Wireless Networks: A Meta-Learning Model-Enabled Scheme」主題。共同形成了獨特的指紋。

引用此