Recent years have seen the explosion of edge intelligence with powerful Deep Neural Networks (DNNs). One popular scheme is training DNNs on powerful cloud servers and subsequently porting them to mobile devices after being lightweight. Conventional approaches manually specialized DNNs for various edge platforms and retrain them with real-world data. However, as the number of platforms increases, these approaches become labour-intensive and computationally prohibitive. Additionally, real-world data tends to be sparse-label, further increasing the difficulty of lightweight models. In this paper, we propose MatchNAS, a novel scheme for porting DNNs to mobile devices. Specifically, we simultaneously optimise a large network family using both labelled and unlabelled data and then automatically search for tailored networks for different hardware platforms. MatchNAS acts as an intermediary that bridges the gap between cloud-based DNNs and edge-based DNNs.

翻译：近年来，随着强大的深度神经网络（DNN）的兴起，边缘智能呈爆发式发展。一种常见方案是在强大的云服务器上训练DNN，随后将其轻量化后移植到移动设备上。传统方法针对不同边缘平台手动定制DNN，并使用真实世界数据对其进行重新训练。然而，随着平台数量的增加，这些方法变得劳动密集且计算成本过高。此外，真实世界数据往往具有稀疏标签的特性，进一步增加了轻量化模型的难度。本文提出MatchNAS，一种将DNN移植到移动设备上的新型方案。具体而言，我们同时利用有标签和无标签数据优化一个大型网络家族，然后自动为不同硬件平台搜索定制化网络。MatchNAS充当了连接云端DNN与边缘DNN的桥梁。