AirNet: Neural Network Transmission Over the Air

Mikolaj Jankowski, Deniz Gündüz, Krystian Mikolajczyk

Abstract: State-of-the-art performance for many edge applications is achieved by deep neural networks (DNNs). Often, these DNNs are location- and time-sensitive, and must be delivered over a wireless channel rapidly and efficiently. In this paper, we introduce AirNet, a family of novel methods that allow DNNs to be efficiently delivered over wireless channels under stringent transmit power and latency constraints. It is a part of a new class of joint source-channel coding methods that maximize the accuracy of the DNNs transmitted to the receiver, rather than recover the DNNs with high fidelity. In AirNet, we propose to directly map the DNN parameters to the transmitted channel symbols, while training the network under the channel constraints with robustness to channel noise. AirNet achieves higher accuracy compared to the separation-based alternatives. We further improve its performance by pruning the network below the available bandwidth, and using bandwidth expansion for significant network parameters. We also exploit unequal error protection (UEP) by selectively expanding the important layers. Finally, we propose an ensemble training approach where networks for different channel conditions can be obtained simultaneously, resolving the impractical memory requirements of training distinct networks for different channel conditions.