# Learning How to Demodulate from Few Pilots via Meta-Learning

## TL;DR

This paper introduces a meta-learning approach for IoT devices to rapidly adapt demodulation techniques using few pilots, addressing challenges posed by non-linear amplifiers and fading channels in sporadic transmissions.

## Contribution

It proposes a novel meta-learning framework that enables quick adaptation of demodulators in IoT scenarios with limited pilot data and device-specific non-linearities.

## Key findings

- Meta-learning improves demodulation accuracy with few pilots.
- The approach outperforms standard learning methods.
- Numerical results confirm faster adaptation and better performance.

## Abstract

Consider an Internet-of-Things (IoT) scenario in which devices transmit sporadically using short packets with few pilot symbols. Each device transmits over a fading channel and is characterized by an amplifier with a unique non-linear transfer function. 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 amplifier's distortion. This paper proposes to tackle this problem using meta-learning. Accordingly, pilots from previous IoT transmissions are used as meta-training in order to learn a demodulator that is able to quickly adapt to new end-to-end channel conditions from few pilots. Numerical results validate the advantages of the approach as compared to training schemes that either do not leverage prior transmissions or apply a standard learning algorithm on previously received data.