Meta-Learning Guided Label Noise Distillation for Robust Signal Modulation Classification

TL;DR

This paper introduces a meta-learning guided label noise distillation approach using a teacher-student network framework to enhance the robustness of automatic modulation classification in noisy label scenarios, crucial for IoT security.

Contribution

It proposes a novel meta-learning guided label noise distillation method with a teacher-student network and multi-view signal technique for robust signal modulation classification.

Findings

Significantly improves AMC performance under label noise.

Enhances robustness of DNNs in complex noise scenarios.

Effective for IoT security applications.

Abstract

Automatic modulation classification (AMC) is an effective way to deal with physical layer threats of the internet of things (IoT). However, there is often label mislabeling in practice, which significantly impacts the performance and robustness of deep neural networks (DNNs). In this paper, we propose a meta-learning guided label noise distillation method for robust AMC. Specifically, a teacher-student heterogeneous network (TSHN) framework is proposed to distill and reuse label noise. Based on the idea that labels are representations, the teacher network with trusted meta-learning divides and conquers untrusted label samples and then guides the student network to learn better by reassessing and correcting labels. Furthermore, we propose a multi-view signal (MVS) method to further improve the performance of hard-to-classify categories with few-shot trusted label samples. Extensive experimental results show that our methods can significantly improve the performance and robustness of signal AMC in various and complex label noise scenarios, which is crucial for securing IoT applications.