Semi-Supervised Learning via Swapped Prediction for Communication Signal Recognition
This addresses the challenge of limited labeled data for communication signal recognition, but it is incremental as it builds on existing SSL techniques.
The paper tackles the problem of overfitting in deep neural networks for communication signal recognition when labeled data is scarce, by proposing a semi-supervised learning method called Swapped Prediction that uses consistency-based regularization with data augmentation, achieving promising results.
Deep neural networks have been widely used in communication signal recognition and achieved remarkable performance, but this superiority typically depends on using massive examples for supervised learning, whereas training a deep neural network on small datasets with few labels generally falls into overfitting, resulting in degenerated performance. To this end, we develop a semi-supervised learning (SSL) method that effectively utilizes a large collection of more readily available unlabeled signal data to improve generalization. The proposed method relies largely on a novel implementation of consistency-based regularization, termed Swapped Prediction, which leverages strong data augmentation to perturb an unlabeled sample and then encourage its corresponding model prediction to be close to its original, optimized with a scaled cross-entropy loss with swapped symmetry. Extensive experiments indicate that our proposed method can achieve a promising result for deep SSL of communication signal recognition.