Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916047178694656 |
|---|---|
| author | Zhao, Guanqun Liu, Yitong Fang, Jiaxuan Mao, Yufei Yang, Hongwen |
| author_facet | Zhao, Guanqun Liu, Yitong Fang, Jiaxuan Mao, Yufei Yang, Hongwen |
| contents | Standard Self-Supervised Learning (SSL) for Automatic Modulation Recognition (AMR) struggles with ineffective isotropic augmentations, spectral instability, and semantic drift. To address these challenges, we propose Dynamic-Consistency Contrastive Learning (DyCo-CL), a geometry-aware framework that couples Virtual Adversarial Augmentation (VAA) with a semantic consistency loss. We provide a theoretical analysis indicating that this strategy acts as an implicit spectral regularizer for the encoder, enabling stable manifold exploration. Complementing this, our Signal-Adaptive Swin Backbone with fixed-window attention improves structural stability by constraining attention locality, while a Hybrid Knowledge Fusion module anchors representations with physical priors. Experiments on RML benchmarks show that DyCo-CL achieves a 6.27% accuracy gain in 1-shot settings over prior methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26600 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition Zhao, Guanqun Liu, Yitong Fang, Jiaxuan Mao, Yufei Yang, Hongwen Machine Learning Artificial Intelligence Standard Self-Supervised Learning (SSL) for Automatic Modulation Recognition (AMR) struggles with ineffective isotropic augmentations, spectral instability, and semantic drift. To address these challenges, we propose Dynamic-Consistency Contrastive Learning (DyCo-CL), a geometry-aware framework that couples Virtual Adversarial Augmentation (VAA) with a semantic consistency loss. We provide a theoretical analysis indicating that this strategy acts as an implicit spectral regularizer for the encoder, enabling stable manifold exploration. Complementing this, our Signal-Adaptive Swin Backbone with fixed-window attention improves structural stability by constraining attention locality, while a Hybrid Knowledge Fusion module anchors representations with physical priors. Experiments on RML benchmarks show that DyCo-CL achieves a 6.27% accuracy gain in 1-shot settings over prior methods. |
| title | Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.26600 |