期刊
IEEE TRANSACTIONS ON SIGNAL PROCESSING
卷 69, 期 -, 页码 226-239出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSP.2020.3043879
关键词
Training; Demodulation; Adaptation models; Decoding; Signal processing algorithms; Task analysis; Numerical models; Machine learning; meta-learning; online meta-learning; Model-Agnostic Meta-Learning (MAML); First-Order MAML (FOMAML); REPTILE; fast Context Adaptation VIA meta-learning (CAVIA); IoT; demodulation
资金
- Institute of Information & Communications Technology Planning & Evaluation (IITP) - Korea Government (MSIT) [2018-0-00170]
- European Research Council (ERC) under the European Union [725731]
- Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center (ITRC) Support Program [IITP-2020-0-01787]
This paper explores the issue of sparse pilot transmission in IoT devices over fading channels, proposing a meta-learning approach to training demodulators to quickly adapt to new channel conditions. By using previous IoT transmissions as meta-training data, the paper demonstrates the advantages of meta-learning over traditional training schemes.
This paper considers an Internet-of-Things (IoT) scenario in which devices sporadically transmit short packets with few pilot symbols over a fading channel. Devices are characterized by unique transmission non-idealities, such as I/Q imbalance. The number of pilots is generally insufficient to obtain an accurate estimate of the end-to-end channel, which includes the effects of fading and of the transmission-side distortion. This paper proposes to tackle this problem by using meta-learning. Accordingly, pilots from previous IoT transmissions are used as meta-training data in order to train a demodulator that is able to quickly adapt to new end-to-end channel conditions from few pilots. Various state-of-the-art meta-learning schemes are adapted to the problem at hand and evaluated, including Model-Agnostic Meta-Learning (MAML), First-Order MAML (FOMAML), REPTILE, and fast Context Adaptation VIA meta-learning (CAVIA). Both offline and online solutions are developed. In the latter case, an integrated online meta-learning and adaptive pilot number selection scheme is proposed. Numerical results validate the advantages of meta-learning as compared to training schemes that either do not leverage prior transmissions or apply a standard joint learning algorithms on previously received data.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据