Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
复制标题
DOI：
10.1145/3527155
复制
发表时间：
2021-03
影响因子：
16.6
通讯作者：
Yoshitomo Matsubara;M. Levorato;Francesco Restuccia
中科院分区：
文献类型：
--
作者：
Yoshitomo Matsubara;M. Levorato;Francesco Restuccia
智能手机和自动驾驶汽车等移动的设备越来越依赖深度神经网络（DNN）来执行复杂的推理任务，如图像分类和语音识别等。然而，在移动的设备上连续执行整个DNN会很快耗尽它们的电池。虽然任务卸载到云/边缘服务器可以减少移动终端的计算负担，但是信道质量、网络和边缘服务器负载中的不稳定模式可能导致任务执行的显著延迟。最近，已经提出了基于分裂计算（SC）的方法，其中DNN被分裂成头部和尾部模型，分别在移动终端和边缘服务器上执行。最终，这可以减少带宽使用以及能量消耗。另一种方法称为提前退出（EE），它训练模型在架构中更早地嵌入多个“出口”，每个出口都提供越来越高的目标准确性。因此，可以根据当前条件或应用需求来调整精度和延迟之间的折衷。在这篇文章中，我们提供了一个全面的调查，最先进的SC和EE战略的比较最相关的方法。我们通过提供一组引人注目的研究挑战来结束这篇文章。
Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously executing the entire DNN on mobile devices can quickly deplete their battery. Although task offloading to cloud/edge servers may decrease the mobile device’s computational burden, erratic patterns in channel quality, network, and edge server load can lead to a significant delay in task execution. Recently, approaches based on split computing (SC) have been proposed, where the DNN is split into a head and a tail model, executed respectively on the mobile device and on the edge server. Ultimately, this may reduce bandwidth usage as well as energy consumption. Another approach, called early exiting (EE), trains models to embed multiple “exits” earlier in the architecture, each providing increasingly higher target accuracy. Therefore, the tradeoff between accuracy and delay can be tuned according to the current conditions or application demands. In this article, we provide a comprehensive survey of the state of the art in SC and EE strategies by presenting a comparison of the most relevant approaches. We conclude the article by providing a set of compelling research challenges.