Universal and complementary representation learning for automatic modulation recognition

Automatic modulation recognition (AMR) is a fundamental research topic in the field of signal processing and wireless communication, which has widespread applications in cognitive radio, non-collaborative communication etc. In this paper, the focus is on the multi-modal utilization in AMR. Specifically, the universal and complementary characteristics of multiple modality data in the domain-agnostic and domain-specific aspects are mined, yielding the universal and complementary subspaces network accordingly (dubbed as UCNet). To facilitate the subspace construction, universal and complementary losses are proposed accordingly. The proposed UCNet has achieved the highest recognition accuracy of 93.2% at 10 dB on the RadioML2016.10A dataset, and the average accuracy is 92.6% at high SNR greater than zero. This paper introduces a multi-modal feature fusion methods for automatic modulation recognition task, which mines the universal and complementary characteristics of the modality data in the domain-agnostic and domain-specific aspects, yielding the universal and complementary subspaces accordingly (dubbed as UCNet). To construct the subspaces, we design universal and complementary losses.image