Machine Learning at the Network Edge: A Survey
By M. G. Sarwar Murshed, Chris Murphy, Daqing Hou, Nazar Khan, Ganesh Ananthanarayanan, Faraz Hussain. ACM Computing Surveys, 2019
512 citations recorded by the source corpus.
Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical solution involves offloading data to external computing systems (such as cloud servers) for further processing but this worsens latency, leads to increased communication costs, and adds to privacy concerns. To address this issue, efforts have been made to place additional computing devices at the edge of the network, i.e., close to the IoT devices where the data is generated. Deploying machine learning systems on such edge computing devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems.
Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Information Systems
View Paper: https://www.semanticscholar.org/paper/3e9a40a567c4a95b591530ff5771296b478a0f0c
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
- H. Vincent Poor
- Yuanming Shi
- Khaled Ben Letaief
- Shuguang Cui
- Mingzhe Chen
- Zhaohui Yang
- Tao Jiang
- Kai Yang
In Computer Vision and Pattern Recognition
- Simone Scardapane
- Michele Scarpiniti
- Enzo Baccarelli
- Aurelio Uncini
- Khaled Ben Letaief
- H. Vincent Poor
- Tao Jiang
- Kai Yang
In Information Systems
- Shuguang Cui
- Khaled Ben Letaief
- H. Vincent Poor
- Michele Scarpiniti
- Enzo Baccarelli
- Yuanming Shi
- Zhaohui Yang
- Mingzhe Chen
Citations in the corpus
- Federated Learning for 6G: Applications, Challenges, and Opportunities (2021, background): “In [22], the authors described the challenges of machine learning systems that are”
- Communication-Efficient Edge AI: Algorithms and Systems (2020, background): “Unlike existing survey papers [9], [10], [39], [40], we shall present a comprehensive coverage to address the communication challenges for realizing AI at network edges.”
- Differentiable Branching In Deep Networks for Fast Inference (2020, background): “Recently, an alternative technique that has obtained considerable interest is to augment the original model (referred to as the backbone) with a set of additional auxiliary classifiers departing from the main network [2, 9– 12].”