TY - GEN
T1 - Few-Shot Learning in Wireless Networks
T2 - 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
AU - Xiong, Kexin
AU - Zhao, Zhongyuan
AU - Hong, Wei
AU - Peng, Mugen
AU - Quek, Tony Q.S.
N1 - Funding Information:
VI. ACHNOWLEDGMENT This work was supported in part by National Natural Science Foundation of China(Grant 61971061), and in part by Beijing Natural Science Foundation(Grant L182039).
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85134750232&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85134750232&partnerID=8YFLogxK
U2 - 10.1109/ICCWorkshops53468.2022.9814634
DO - 10.1109/ICCWorkshops53468.2022.9814634
M3 - Conference contribution
AN - SCOPUS:85134750232
T3 - 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
SP - 415
EP - 420
BT - 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 16 May 2022 through 20 May 2022
ER -