ModFus-DM: Explore the Representation in Modulated Signal Diffusion Generated Models
Preprint
Abstract
Automatic modulation classification (AMC) is essential for wireless communication systems in both military and civilian applications. However, existing deep learning-based AMC methods often require large labeled signals and struggle with non-fixed signal lengths, distribution shifts, and limited labeled signals. To address these challenges, we propose a modulation-driven feature fusion via diffusion model (ModFus-DM), a novel unsupervised AMC framework that leverages the generative capacity of diffusion models for robust modulation representation learning. We design a modulated signal diffusion generation model (MSDGM) to implicitly capture structural and semantic information through a progressive denoising process. Additionally, we propose the diffusion-aware feature fusion (DAFFus) module, which adaptively aggregates multi-scale diffusion features to enhance discriminative representation. Extensive experiments on RML2016.10A, RML2016.10B, RML2018.01A and RML2022 datasets demonstrate that ModFus-DM significantly outperforms existing methods in various challenging scenarios, such as limited-label settings, distribution shifts, variable-length signal recognition and channel fading scenarios. Notably, ModFus-DM achieves over 88.27% accuracy in 24-type recognition tasks at SNR $\geq $ 12dB with only 10 labeled signals per type.
Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Multi-representation domain attentive contrastive learning based unsupervised automatic modulation recognitionNature Communications, 2025
- Diffusion Model Empowered Data Augmentation for Automatic Modulation RecognitionIEEE Wireless Communications Letters, 2025
- Hybrid-View Self-Supervised Framework for Automatic Modulation RecognitionIEEE Internet of Things Journal, 2024
- Multi-Scale Feature Fusion and Distribution Similarity Network for Few-Shot Automatic Modulation ClassificationIEEE Signal Processing Letters, 2024
- Open Set Recognition of Communication Signal Modulation Based on Deep LearningIEEE Communications Letters, 2022
- Shared Spectrum Monitoring Using Deep LearningIEEE Transactions on Cognitive Communications and Networking, 2021
- An Efficient Deep Learning Model for Automatic Modulation Recognition Based on Parameter Estimation and TransformationIEEE Communications Letters, 2021
- SSRCNN: A Semi-Supervised Learning Framework for Signal RecognitionIEEE Transactions on Cognitive Communications and Networking, 2021
- A Spatiotemporal Multi-Channel Learning Framework for Automatic Modulation RecognitionIEEE Wireless Communications Letters, 2020
- Over-the-Air Deep Learning Based Radio Signal ClassificationIEEE Journal of Selected Topics in Signal Processing, 2018