Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promising approach. It allows the power of DNNs to be leveraged for latency-sensitive applications that do not allow the entire DNN to be deployed remotely, while not having sufficient computation bandwidth available locally. In many such embedded systems scenarios, such as those in the automotive domain, computational resource constraints also necessitate Multi-Task Learning (MTL), where the same DNN is used for multiple inference tasks instead of having dedicated DNNs for each task, which would need more computing bandwidth. However, how to partition such a multi-tasking DNN to be deployed within a SC framework has not been sufficiently studied. This paper studies this problem, and MTL-Split, our novel proposed architecture, shows encouraging results on both synthetic and real-world data. The source code is available at https://github.com/intelligolabs/MTL-Split.

翻译：分割计算（Split Computing, SC）作为一种新兴且前景广阔的方法，其核心思想是将深度神经网络（DNN）进行智能分割，一部分部署在边缘设备上，其余部分则部署在远程服务器上。这种方法使得DNN的能力能够被应用于对延迟敏感的场景中，这些场景既不允许将整个DNN完全远程部署，而本地又缺乏足够的计算带宽。在许多此类嵌入式系统场景中（例如汽车领域），计算资源的限制也催生了对多任务学习（Multi-Task Learning, MTL）的需求，即使用同一个DNN来执行多个推理任务，而不是为每个任务配备专用的DNN（后者需要更多的计算带宽）。然而，如何分割这样一个多任务DNN以便将其部署在SC框架内，尚未得到充分研究。本文研究了这一问题，我们提出的新颖架构MTL-Split在合成数据和真实世界数据上都取得了令人鼓舞的结果。源代码可在 https://github.com/intelligolabs/MTL-Split 获取。