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.

使用深度神经网络进行通信信号识别在大样本监督学习方面表现出色，但对于小数据集和少量标签的情况下，使用深度神经网络进行训练往往容易过拟合，性能下降。为此，我们提出了一种半监督学习方法，能够有效利用大量的未标记信号数据来提高泛化能力。该方法主要依赖于一种新颖的一致性正则化实现，即 Swapped Prediction，它利用强大的数据增强来扰动一个未标记样本，并鼓励其对应的模型预测接近其原始预测，该预测经过交叉熵损失的缩放对称优化。广泛的实验证明，我们提出的方法在通信信号识别的深度半监督学习方面取得了有希望的结果。