English

Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition

Machine Learning 2026-05-27 v1 Artificial Intelligence

Abstract

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.

Cite

@article{arxiv.2605.26600,
  title  = {Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition},
  author = {Guanqun Zhao and Yitong Liu and Jiaxuan Fang and Yufei Mao and Hongwen Yang},
  journal= {arXiv preprint arXiv:2605.26600},
  year   = {2026}
}