State-of-the-art performance for many emerging edge applications is achieved by deep neural networks (DNNs). Often, these DNNs are location and time sensitive, and the parameters of a specific DNN must be delivered from an edge server to the edge device rapidly and efficiently to carry out time-sensitive inference tasks. We introduce AirNet, a novel training and analog transmission method that allows efficient wireless delivery of DNNs. We first train the DNN with noise injection to counter the wireless channel noise. We also employ pruning to reduce the channel bandwidth necessary for transmission, and perform knowledge distillation from a larger model to achieve satisfactory performance, despite the channel perturbations. We show that AirNet achieves significantly higher test accuracy compared to digital alternatives under the same bandwidth and power constraints. It also exhibits graceful degradation with channel quality, which reduces the requirement for accurate channel estimation.
翻译:许多新兴边缘应用的最先进的性能是由深神经网络(DNNs)实现的。这些DNNs通常对位置和时间敏感,而特定的DNN的参数必须从边缘服务器迅速、高效地从边缘服务器传送到边缘装置,以完成时间敏感推理任务。我们引入了AirNet,这是一个新培训和模拟传输方法,允许高效无线传送DNes。我们首先用注入噪音的方式对DNN进行DN进行测试,以对抗无线频道的噪音。我们还利用修剪,以减少传输所需的频道带宽,并用更大的模型进行知识蒸馏,以达到令人满意的性能。我们表明,AirNet在相同的带宽和功率限制下,与数字替代方法相比,其测试精度要高得多。它还显示出频道质量的优劣,从而降低了对频道进行准确估计的要求。