Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
By Zhi Zhou, Xu Chen, En Li, Liekang Zeng, Ke Luo, Junshan Zhang. 2019
1,896 citations recorded by the source corpus.
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 interdiscipline, edge AI or edge intelligence (EI), is beginning to receive a tremendous amount of interest. However, research on EI is still in its infancy stage, and a dedicated venue for exchanging the recent advances of EI is highly desired by both the computer system and AI communities. To this end, we conduct a comprehensive survey of the recent research efforts on EI. Specifically, we first review the background and motivation for AI running at the network edge. We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Finally, we discuss future research opportunities on EI. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions, and inspire further research ideas on EI.
Subfields: Artificial Intelligence, Computer Networks and Communications, Computer Vision and Pattern Recognition, ML Systems & Hardware
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Networks and Communications
- Khaled Ben Letaief
- Rui Zhang
- Jun Zhang
- Jie Xu
- Qingqing Wu
- Robert Schober
- Xu Chen
- Derrick Wing Kwan Ng
In Computer Vision and Pattern Recognition
In ML Systems & Hardware
Citations in the corpus
- Why Should We Add Early Exits to Neural Networks? (2020, background): “…ranging from 5G cellular networks to IoT sensors and fog computing, are built upon the idea of multi-tier computations, in which decisions can be taken both at the edge of the networks or delegated to other, more powerful decision centers that incur some communication latency [ 57, 79 ] .”
- A Survey on Federated Learning for Resource-Constrained IoT Devices (2021, neutral): “On the other hand, edge computing surveys [13]– [19] are mainly conducted on edge computing infrastructure, applications including ML and AI, resource management, wireless communication, and security and privacy issues.”
- SAFA: A Semi-Asynchronous Protocol for Fast Federated Learning With Low Overhead (2019, positive): “[13] summarizes recent studies on edge intelligence and lists FL as one of the most uprising technologies for distributed training at the edge.”
- Federated Learning in Edge Computing: A Systematic Survey (2022, background): “…edge computing paradigms X X X X [6] Survey on the integrated management of mobile computing and wireless communication resources in MEC X X X [63] Edge intelligence architectures and frameworks’ survey X X X X [64] Survey on edge intelligence specifically for 6G networks X X X [65] Management…”
- Edge Computing with Artificial Intelligence: A Machine Learning Perspective (2022, methodology): “In Reference [11], authors focus on the motivation and research work of deploying AI algorithm on the edge of the network.”
- User-Centric Cell-Free Massive MIMO Networks: A Survey of Opportunities, Challenges and Solutions (2021, background): “Still, the federated learning framework looks interesting, especially with the growing use of on-mobile artificial intelligence (AI) [260, 261].”
- Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “In particular, the authors in [14], [37], and [38] study the architectures and process of training and inference at edge networks without considering the challenges to FL implementation.”
- Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review (2023, methodology): “The EI of DL models can be categorized into three types [18]: 1) inference on the edge server; 2) inference on the edge device; and 3) collaborative inference on the edge device and edge server.”
- A Comprehensive Overview on 5G-and-Beyond Networks With UAVs: From Communications to Sensing and Intelligence (2020, background): “porated into BSs and APs at the network edge, for enabling various intelligent applications (such as autonomous driving and industrial automation) with extensive communication and computation requirements [293], [294].”
- Multimodal biomedical AI (2022, background): “An additional layer of safety can be obtained by leveraging novel developments in edge computing 171 .”
- Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge Based Framework (2020, background): “To tackle the high communication and computation cost issues in device heterogeneity, we resort to edge computing which brings the necessary on-demand computing power in the proximity of IoT devices [2].”
- A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges (2022, methodology): “…and distributed security mechanism designs can be designed to establish user authentication and access control, model/data integrity, and mutual platform verification [8]. d) The use of federated learning, blockchain, or the integration of both (e.g., [37]) can further improve security/privacy.”
- Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services (2023, neutral): “Although AIGC is acknowledged for its potential to revolutionize existing production processes, users accessing AIGC services on mobile devices currently lack support for interactive and resource-intensive data generation services [1], [18], [29].”
- AI for Next Generation Computing: Emerging Trends and Future Directions (2022, neutral): “elp automated processes is supplied [115].”
- HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learning (2020, background): “AS MOBILE and internet of things (IoT) devices have emerged in large numbers and are generating a massive amount of data [1], Machine Learning (ML) has been witnessed to go through a high-speed development due to big”
- Communication-Efficient Edge AI: Algorithms and Systems (2020, background): “To unleash its full potential, the upcoming edge AI [9], [18] shall rely on advances in various aspects, including the smart design of distributed learning algorithms and system architectures, supported by efficient communication protocols.”
- Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning (2020, background): “Therefore, the model accuracy within certain training time budgets (i.e., convergence rate w.r.t. time ), which is critical for latency constrained FL applications [27], [28], has not been addressed yet.”
- Edge Computing in Industrial Internet of Things: Architecture, Advances and Challenges (2020, methodology): “Therefore, deploying AI algorithms on edge devices can theoretically achieve the complementary combination of edge computing and AI [127].”