Robust Automatic Modulation Classification with Fuzzy Regularization

Xinyan Liang, Ruijie Sang, Yuhua Qian, Qian Guo, Feijiang Li, Liang Du
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37396-37408, 2025.

Abstract

Automatic Modulation Classification (AMC) serves as a foundational pillar for cognitive radio systems, enabling critical functionalities including dynamic spectrum allocation, non-cooperative signal surveillance, and adaptive waveform optimization. However, practical deployment of AMC faces a fundamental challenge: prediction ambiguity arising from intrinsic similarity among modulation schemes and exacerbated under low signal-to-noise ratio (SNR) conditions. This phenomenon manifests as near-identical probability distributions across confusable modulation types, significantly degrading classification reliability. To address this, we propose Fuzzy Regularization-enhanced AMC (FR-AMC), a novel framework that integrates uncertainty quantification into the classification pipeline. The proposed FR has three features: (1) Explicitly model prediction ambiguity during backpropagation, (2) dynamic sample reweighting through adaptive loss scaling, (3) encourage margin maximization between confusable modulation clusters. Experimental results on benchmark datasets demonstrate that the FR achieves superior classification accuracy and robustness compared to compared methods, making it a promising solution for real-world spectrum management and communication applications.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-liang25o, title = {Robust Automatic Modulation Classification with Fuzzy Regularization}, author = {Liang, Xinyan and Sang, Ruijie and Qian, Yuhua and Guo, Qian and Li, Feijiang and Du, Liang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {37396--37408}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/liang25o/liang25o.pdf}, url = {https://proceedings.mlr.press/v267/liang25o.html}, abstract = {Automatic Modulation Classification (AMC) serves as a foundational pillar for cognitive radio systems, enabling critical functionalities including dynamic spectrum allocation, non-cooperative signal surveillance, and adaptive waveform optimization. However, practical deployment of AMC faces a fundamental challenge: prediction ambiguity arising from intrinsic similarity among modulation schemes and exacerbated under low signal-to-noise ratio (SNR) conditions. This phenomenon manifests as near-identical probability distributions across confusable modulation types, significantly degrading classification reliability. To address this, we propose Fuzzy Regularization-enhanced AMC (FR-AMC), a novel framework that integrates uncertainty quantification into the classification pipeline. The proposed FR has three features: (1) Explicitly model prediction ambiguity during backpropagation, (2) dynamic sample reweighting through adaptive loss scaling, (3) encourage margin maximization between confusable modulation clusters. Experimental results on benchmark datasets demonstrate that the FR achieves superior classification accuracy and robustness compared to compared methods, making it a promising solution for real-world spectrum management and communication applications.} }
Endnote
%0 Conference Paper %T Robust Automatic Modulation Classification with Fuzzy Regularization %A Xinyan Liang %A Ruijie Sang %A Yuhua Qian %A Qian Guo %A Feijiang Li %A Liang Du %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-liang25o %I PMLR %P 37396--37408 %U https://proceedings.mlr.press/v267/liang25o.html %V 267 %X Automatic Modulation Classification (AMC) serves as a foundational pillar for cognitive radio systems, enabling critical functionalities including dynamic spectrum allocation, non-cooperative signal surveillance, and adaptive waveform optimization. However, practical deployment of AMC faces a fundamental challenge: prediction ambiguity arising from intrinsic similarity among modulation schemes and exacerbated under low signal-to-noise ratio (SNR) conditions. This phenomenon manifests as near-identical probability distributions across confusable modulation types, significantly degrading classification reliability. To address this, we propose Fuzzy Regularization-enhanced AMC (FR-AMC), a novel framework that integrates uncertainty quantification into the classification pipeline. The proposed FR has three features: (1) Explicitly model prediction ambiguity during backpropagation, (2) dynamic sample reweighting through adaptive loss scaling, (3) encourage margin maximization between confusable modulation clusters. Experimental results on benchmark datasets demonstrate that the FR achieves superior classification accuracy and robustness compared to compared methods, making it a promising solution for real-world spectrum management and communication applications.
APA
Liang, X., Sang, R., Qian, Y., Guo, Q., Li, F. & Du, L.. (2025). Robust Automatic Modulation Classification with Fuzzy Regularization. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:37396-37408 Available from https://proceedings.mlr.press/v267/liang25o.html.

Related Material