Self-Contrastive Learning based Semi-Supervised Radio Modulation Classification

TL;DR

This paper introduces a semi-supervised learning framework for automatic modulation classification that leverages self-supervised contrastive pre-training to improve performance with less labeled data.

Contribution

It presents a novel semi-supervised approach using contrastive learning specifically designed for AMC, reducing the need for extensive labeled datasets.

Findings

Semi-supervised framework outperforms supervised methods

Significant performance gains with limited labeled data

Effective utilization of unlabeled signal data

Abstract

This paper presents a semi-supervised learning framework that is new in being designed for automatic modulation classification (AMC). By carefully utilizing unlabeled signal data with a self-supervised contrastive-learning pre-training step, our framework achieves higher performance given smaller amounts of labeled data, thereby largely reducing the labeling burden of deep learning. We evaluate the performance of our semi-supervised framework on a public dataset. The evaluation results demonstrate that our semi-supervised approach significantly outperforms supervised frameworks thereby substantially enhancing our ability to train deep neural networks for automatic modulation classification in a manner that leverages unlabeled data.