Deep Learning With Edge Computing: A Review

By Jiasi Chen, Xukan Ran. Proceedings of the IEEE, 2019

1,289 citations recorded by the source corpus.

Deep learning is currently widely used in a variety of applications, including computer vision and natural language processing. End devices, such as smartphones and Internet-of-Things sensors, are generating data that need to be analyzed in real time using deep learning or used to train deep learning models. However, deep learning inference and training require substantial computation resources to run quickly. Edge computing, where a fine mesh of compute nodes are placed close to end devices, is a viable way to meet the high computation and low-latency requirements of deep learning on edge devices and also provides additional benefits in terms of privacy, bandwidth efficiency, and scalability. This paper aims to provide a comprehensive review of the current state of the art at the intersection of deep learning and edge computing. Specifically, it will provide an overview of applications where deep learning is used at the network edge, discuss various approaches for quickly executing deep learning inference across a combination of end devices, edge servers, and the cloud, and describe the methods for training deep learning models across multiple edge devices. It will also discuss open challenges in terms of systems performance, network technologies and management, benchmarks, and privacy. The reader will take away the following concepts from this paper: understanding scenarios where deep learning at the network edge can be useful, understanding common techniques for speeding up deep learning inference and performing distributed training on edge devices, and understanding recent trends and opportunities.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4f2d4e821dd03ac5df7d5448948bc738aefdd6db

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Machine Learning at the Network Edge: A Survey (2019, background): “In the last few years, edge computing is being increasingly used for the deployment of ML based intelligent systems in resource-constrained environments [25, 145, 150, 165, 166], which is the motivation for this survey.”
Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges (2021, background): “Recently, edge computing (EC) approaches [10, 88] have attempted to address the “latency vs computation” conundrum by completely offloading the DNN execution to servers located very close to the mobile device, i.”
Edge Machine Learning for AI-Enabled IoT Devices: A Review (2020, background): “The target of secure computation [66] is to ensure that the end device receives an inference result without learning anything about the DNN model on the edge server and vice versa.”
Edge Computing with Artificial Intelligence: A Machine Learning Perspective (2022, methodology): “Various methods of fast implementation of DL reasoning in the combination of end devices, edge servers and cloud, and the methods of training DL models in multiple edge devices are also discussed in Reference [14].”
End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things (2020, background): “Indeed, as highlighted in [16], there is a demand to understand the deep learning performances on resource-constrained IoT/edge device hardware like Raspberry Pi [17].”
Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review (2023, methodology): “There are available reviews of different DL techniques [5], DNNs on edge [2], [16], DL compression techniques for hardware acceleration [10], DL inference on FPGA-based platforms [17], edge intelligence [18], and edge computing [19].”
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference (2020, background): “However, complex deep learning models are impractical for low-power edge devices, such as an Arduino, that are common in the IoT scenarios (Chen & Ran, 2019).”