TY - JOUR
T1 - Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
AU - Park, Sangwoo
AU - Jang, Hyeryung
AU - Simeone, Osvaldo
AU - Kang, Joonhyuk
N1 - Publisher Copyright:
© 1991-2012 IEEE.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - demodulation
KW - fast Context Adaptation VIA meta-learning (CAVIA)
KW - First-Order MAML (FOMAML)
KW - IoT
KW - Machine learning
KW - meta-learning
KW - Model-Agnostic Meta-Learning (MAML)
KW - online meta-learning
KW - REPTILE
UR - http://www.scopus.com/inward/record.url?scp=85097956054&partnerID=8YFLogxK
U2 - 10.1109/TSP.2020.3043879
DO - 10.1109/TSP.2020.3043879
M3 - Article
AN - SCOPUS:85097956054
SN - 1053-587X
VL - 69
SP - 226
EP - 239
JO - IEEE Transactions on Signal Processing
JF - IEEE Transactions on Signal Processing
M1 - 9290055
ER -