[论文解读] Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing

Zhi Zhou, Xu Chen+4 more|arXiv (Cornell University)|May 24, 2019

IoT and Edge/Fog Computing参考文献 108被引用 98

一句话总结

这是对边缘智能（edge AI）的全面综述，概述了推动 AI 到网络边缘的动机、定义、体系结构、训练/推理方法、使能技术以及未来研究方向。

ABSTRACT

With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet-of-Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions Bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new inter-discipline, edge AI or edge intelligence, is beginning to receive a tremendous amount of interest. However, research on edge intelligence is still in its infancy stage, and a dedicated venue for exchanging the recent advances of edge intelligence is highly desired by both the computer system and artificial intelligence communities. To this end, we conduct a comprehensive survey of the recent research efforts on edge intelligence. Specifically, we first review the background and motivation for artificial intelligence running at the network edge. We then provide an overview of the overarching architectures, frameworks and emerging key technologies for deep learning model towards training/inference at the network edge. Finally, we discuss future research opportunities on edge intelligence. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions and inspire further research ideas on edge intelligence.

研究动机与目标

• 促使并定义边缘智能及其超越传统云端 AI 的好处。
• 提出一个覆盖从云端为中心到全在设备上执行的多层级边缘智能评级框架。
• 综述边缘AI训练与推理的架构、系统和框架。
• 识别推动边缘智能的使能技术与公开挑战。
• 强调边缘AI研究与实践的未来方向。

提出的方法

• 提供对背景 AI 概念的结构化综述，重点放在深度学习模型上。
• 定义边缘智能并引入一个六级评级（云端到全在设备上）以进行边缘 AI 部署。
• 将分布式 DNN 训练体系结构分为集中化、去中心化和混合（云–边–设备）。
• 回顾边缘 AI 模型训练与推理的架构、技术与系统。
• 总结使能技术（如 Federated Learning、梯度压缩、DNN 拆分）及其对关键性能指标的影响。
• 讨论边缘智能的未来机会与未解决挑战。

实验结果

研究问题

• RQ1 边缘智能的动机、定义和评级方案是什么？
• RQ2 哪些架构与使能技术在云、边、设备层面支持边缘AI训练和推理？
• RQ3 在边缘智能各级别中，延迟、隐私、通信成本和能效如何权衡，有哪些合适的解决方案？
• RQ4 边缘智能研究与实践的开放挑战和未来方向有哪些？

主要发现

• 边缘智能将边缘计算与 AI 相结合，通过在数据源附近利用边缘资源实现低延迟、注重隐私的 AI。
• 六级评级框架（从 cloud intelligence 到全在设备上）有助于描述训练与推理发生在何处，以及每一级数据卸载如何变化。
• 在边缘的分布式 DNN 训练可以遵循集中化、去中心化或混合架构，每种架构都有不同的数据流和隐私影响。
• 本文回顾了使能技术，如 Federated Learning、梯度压缩、DNN 拆分和知识迁移，以提高训练效率和隐私性。
• 它讨论了边缘训练的关键性能指标（训练损失、收敛性、隐私、通信成本、延迟、能量）及其权衡。
• 指出边缘智能的开放挑战和未来方向，旨在促进进一步研究和实际部署。