MDM: Advancing Multi-Domain Distribution Matching for Automatic Modulation Recognition Dataset Synthesis

TL;DR

This paper introduces MDM, a novel dataset distillation method for automatic modulation recognition that uses multi-domain distribution matching in time and frequency domains, achieving better performance with smaller datasets.

Contribution

The paper proposes MDM, a new dataset distillation technique leveraging multi-domain distribution matching for AMR, addressing the unique signal features across domains.

Findings

MDM outperforms baseline methods at the same compression ratio.

Synthetic datasets generated by MDM generalize well across different models.

Extensive experiments validate the effectiveness of MDM on multiple datasets.

Abstract

Recently, deep learning technology has been successfully introduced into Automatic Modulation Recognition (AMR) tasks. However, the success of deep learning is all attributed to the training on large-scale datasets. Such a large amount of data brings huge pressure on storage, transmission and model training. In order to solve the problem of large amount of data, some researchers put forward the method of data distillation, which aims to compress large training data into smaller synthetic datasets to maintain its performance. While numerous data distillation techniques have been developed within the realm of image processing, the unique characteristics of signals set them apart. Signals exhibit distinct features across various domains, necessitating specialized approaches for their analysis and processing. To this end, a novel dataset distillation method--Multi-domain Distribution Matching (MDM) is proposed. MDM employs the Discrete Fourier Transform (DFT) to translate timedomain signals into the frequency domain, and then uses a model to compute distribution matching losses between the synthetic and real datasets, considering both the time and frequency domains. Ultimately, these two losses are integrated to update the synthetic dataset. We conduct extensive experiments on three AMR datasets. Experimental results show that, compared with baseline methods, our method achieves better performance under the same compression ratio. Furthermore, we conduct crossarchitecture generalization experiments on several models, and the experimental results show that our synthetic datasets can generalize well on other unseen models.