Li Yu, Shi Xiaoran, Tan Haoyue, Zhang Zhenxi, Yang Xinyao, Zhou Feng
Key Laboratory of Electronic Information Countermeasure and Simulation Technology, School of Electronic Engineering, Xidian University, Xi'an, China.
School of Aerospace Science and Technology, Xidian University, Xi'an, China.
Nat Commun. 2025 Jul 1;16(1):5951. doi: 10.1038/s41467-025-60921-z.
The rapid advancement of B5G/6G and wireless technologies, combined with rising end-user numbers, has intensified radio spectrum congestion. Automatic modulation recognition, crucial for spectrum sensing in cognitive radio, traditionally relies on supervised methods requiring extensive labeled data. However, acquiring reliable labels is challenging. Here, we propose an unsupervised framework, Multi-Representation Domain Attentive Contrastive Learning, which extracts high-quality signal features from unlabeled data via cross-domain contrastive learning. Inter-domain and intra-domain contrastive mechanisms enhance mutual modulation feature extraction across domains while preserving source domain self-information. The domain attention module dynamically selects representation domains at the feature level, improving adaptability. The experiments through public datasets show that the proposed method outperforms existing modulation recognition methods and can be extended to accommodate various representation domains. This study bridges the gap between unsupervised and supervised learning for radio signals, advancing Internet of Things and cognitive radio development.
B5G/6G和无线技术的迅速发展，再加上终端用户数量的不断增加，加剧了无线电频谱拥堵。自动调制识别对于认知无线电中的频谱感知至关重要，传统上依赖于需要大量标注数据的监督方法。然而，获取可靠的标签具有挑战性。在此，我们提出了一个无监督框架——多表示域注意力对比学习，它通过跨域对比学习从未标注数据中提取高质量信号特征。域间和域内对比机制增强了跨域的互调制特征提取，同时保留源域自信息。域注意力模块在特征层面动态选择表示域，提高了适应性。通过公共数据集进行的实验表明，所提出的方法优于现有的调制识别方法，并且可以扩展以适应各种表示域。本研究弥合了无线电信号无监督学习和监督学习之间的差距，推动了物联网和认知无线电的发展。
