Self-Supervised RF Signal Representation Learning for NextG Signal Classification with Deep Learning

TL;DR

This paper introduces a self-supervised learning approach for RF signal representation that significantly enhances modulation recognition accuracy and sample efficiency, reducing the need for labeled data in wireless signal classification.

Contribution

The paper proposes a novel self-supervised RF signal representation learning method tailored for wireless signals, improving modulation recognition performance with limited labeled data.

Findings

SSL increases sample efficiency by nearly tenfold.

SSL improves accuracy over state-of-the-art methods.

SSL maintains high accuracy with limited training data.

Abstract

Deep learning (DL) finds rich applications in the wireless domain to improve spectrum awareness. Typically, DL models are either randomly initialized following a statistical distribution or pretrained on tasks from other domains in the form of transfer learning without accounting for the unique characteristics of wireless signals. Self-supervised learning (SSL) enables the learning of useful representations from Radio Frequency (RF) signals themselves even when only limited training data samples with labels are available. We present a self-supervised RF signal representation learning method and apply it to the automatic modulation recognition (AMR) task by specifically formulating a set of transformations to capture the wireless signal characteristics. We show that the sample efficiency (the number of labeled samples needed to achieve a certain performance) of AMR can be significantly increased (almost an order of magnitude) by learning signal representations with SSL. This translates to substantial time and cost savings. Furthermore, SSL increases the model accuracy compared to the state-of-the-art DL methods and maintains high accuracy when limited training data is available.