Enabling All In-Edge Deep Learning: A Literature Review

TL;DR

This literature review explores the all in-edge deep learning paradigm, focusing on architectures, enabling technologies, model adaptation, performance metrics, and future research challenges for deploying DL solely on edge servers.

Contribution

It provides a comprehensive overview of all in-edge deep learning, including architectures, enabling techniques, adaptation methods, and evaluation metrics, highlighting open challenges in the field.

Findings

All in-edge architectures include centralized, decentralized, and distributed models.

Enabling technologies like model parallelism and split learning facilitate edge DL deployment.

Key performance metrics for all in-edge DL include latency, communication cost, and resource utilization.

Abstract

In recent years, deep learning (DL) models have demonstrated remarkable achievements on non-trivial tasks such as speech recognition and natural language understanding. One of the significant contributors to its success is the proliferation of end devices that acted as a catalyst to provide data for data-hungry DL models. However, computing DL training and inference is the main challenge. Usually, central cloud servers are used for the computation, but it opens up other significant challenges, such as high latency, increased communication costs, and privacy concerns. To mitigate these drawbacks, considerable efforts have been made to push the processing of DL models to edge servers. Moreover, the confluence point of DL and edge has given rise to edge intelligence (EI). This survey paper focuses primarily on the fifth level of EI, called all in-edge level, where DL training and inference (deployment) are performed solely by edge servers. All in-edge is suitable when the end devices have low computing resources, e.g., Internet-of-Things, and other requirements such as latency and communication cost are important in mission-critical applications, e.g., health care. Firstly, this paper presents all in-edge computing architectures, including centralized, decentralized, and distributed. Secondly, this paper presents enabling technologies, such as model parallelism and split learning, which facilitate DL training and deployment at edge servers. Thirdly, model adaptation techniques based on model compression and conditional computation are described because the standard cloud-based DL deployment cannot be directly applied to all in-edge due to its limited computational resources. Fourthly, this paper discusses eleven key performance metrics to evaluate the performance of DL at all in-edge efficiently. Finally, several open research challenges in the area of all in-edge are presented.