当前位置: X-MOL 学术IEEE Signal Process. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Adversarial Transfer Learning for Deep Learning Based Automatic Modulation Classification
IEEE Signal Processing Letters ( IF 3.9 ) Pub Date : 2020-01-01 , DOI: 10.1109/lsp.2020.2991875
Ke Bu , Yuan He , Xiaojun Jing , Jindong Han

Automatic modulation classification facilitates many important signal processing applications. Recently, deep learning models have been adopted in modulation recognition, which outperform traditional machine learning techniques based on hand-crafted features. However, automatic modulation classification is still challenging due to the following reasons. Existing deep learning methods are only applicable to the data of the same distribution. In practical scenarios, data distribution is varying with sampling frequency, thus domains with different sampling rates are formed. Besides, it is difficult to construct large-scale well-annotated datasets for all domains of interest. We define the domain with sufficient data as the source domain, while the domain with insufficient data as the target domain. Obviously, the classification model performs weakly in the target domain. To address these challenges, we propose an adversarial transfer learning architecture (ATLA), incorporating adversarial training and knowledge transfer in a unified way. Adversarial training performs an asymmetric mapping between domains and reduces the domain shift. Knowledge transfer is used to mine prior knowledge from the source domain. Experimental results demonstrate that the proposed ATLA substantially boosts the performance of the target model, which outperforms the existing parameter-transfer approach. With half of the training data reduced, the target model achieves competitive recognition accuracy to supervised learning. With one-tenth of training data, the promoted accuracy is up to 17.3% points.

中文翻译:

基于深度学习的自动调制分类的对抗性迁移学习

自动调制分类促进了许多重要的信号处理应用。最近,在调制识别中采用了深度学习模型,其性能优于基于手工特征的传统机器学习技术。然而,由于以下原因,自动调制分类仍然具有挑战性。现有的深度学习方法只适用于相同分布的数据。在实际场景中,数据分布随采样频率而变化,从而形成不同采样率的域。此外,很难为所有感兴趣的领域构建大规模的标注良好的数据集。我们将数据充足的域定义为源域,将数据不足的域定义为目标域。明显地,分类模型在目标域中表现不佳。为了应对这些挑战,我们提出了一种对抗性迁移学习架构(ATLA),以统一的方式结合对抗性训练和知识迁移。对抗训练在域之间执行非对称映射并减少域转移。知识转移用于从源域中挖掘先验知识。实验结果表明,所提出的 ATLA 大大提高了目标模型的性能,优于现有的参数传递方法。通过减少一半的训练数据,目标模型实现了与监督学习竞争的识别准确率。使用十分之一的训练数据,提升的准确率高达 17.3%。我们提出了一种对抗性迁移学习架构(ATLA),以统一的方式结合了对抗性训练和知识迁移。对抗训练在域之间执行非对称映射并减少域转移。知识转移用于从源域中挖掘先验知识。实验结果表明,所提出的 ATLA 大大提高了目标模型的性能,优于现有的参数传递方法。通过减少一半的训练数据,目标模型实现了与监督学习竞争的识别准确率。使用十分之一的训练数据,提升的准确率高达 17.3%。我们提出了一种对抗性迁移学习架构(ATLA),以统一的方式结合了对抗性训练和知识迁移。对抗训练在域之间执行非对称映射并减少域转移。知识转移用于从源域中挖掘先验知识。实验结果表明,所提出的 ATLA 大大提高了目标模型的性能,优于现有的参数传递方法。通过减少一半的训练数据,目标模型实现了与监督学习竞争的识别准确率。使用十分之一的训练数据,提升的准确率高达 17.3%。对抗训练在域之间执行非对称映射并减少域转移。知识转移用于从源域中挖掘先验知识。实验结果表明,所提出的 ATLA 大大提高了目标模型的性能,优于现有的参数传递方法。通过减少一半的训练数据,目标模型实现了与监督学习竞争的识别准确率。使用十分之一的训练数据,提升的准确率高达 17.3%。对抗训练在域之间执行非对称映射并减少域转移。知识转移用于从源域中挖掘先验知识。实验结果表明,所提出的 ATLA 大大提高了目标模型的性能,优于现有的参数传递方法。通过减少一半的训练数据,目标模型实现了与监督学习竞争的识别准确率。使用十分之一的训练数据,提升的准确率高达 17.3%。通过减少一半的训练数据,目标模型实现了与监督学习竞争的识别准确率。使用十分之一的训练数据,提升的准确率高达 17.3%。通过减少一半的训练数据,目标模型实现了与监督学习竞争的识别准确率。使用十分之一的训练数据,提升的准确率高达 17.3%。
更新日期:2020-01-01
down
wechat
bug