Modern edge devices, such as cameras, drones, and Internet-of-Things nodes, rely on deep learning to enable a wide range of intelligent applications. However, this deep learning inference is usually disaggregated: the model is stored on the cloud, while the inputs/outputs are obtained/required on the edge. To this end, we present a novel disaggregated computing architecture for wireless edge networks with two key innovations: disaggregated model access via over-the-air wireless broadcasting for simultaneous inference on multiple edge devices, and in-physics computation of general matrix-vector multiplications directly at radio frequency driven by a single frequency mixer. Using an experimental software-defined radio platform, it achieves 95.7\% image classification accuracy with ultra-low energy consumption of more than two orders of magnitude improvement compared to traditional digital computing.

Zhihui Gao is a final-year Ph.D. Student co-advised by Prof. Tingjun Chen and Prof. Yiran Chen at Duke University. His research interest is the next generation of network systems, machine learning acceleration, and cyber-physical systems. His work has been published in top venues such as Science Advances, ACM MobiCom, ACM MobiHoc, and ACM/IEEE IPSN.