Towards an Intelligent Edge: Wireless Communication Meets Machine Learning

By Guangxu Zhu, Dongzhu Liu, Yuqing Du, Changsheng You, Jun Zhang, Kaibin Huang. 2018

580 citations recorded by the source corpus.

The recent revival of artificial intelligence (AI) is revolutionizing almost every branch of science and technology. Given the ubiquitous smart mobile gadgets and Internet of Things (IoT) devices, it is expected that a majority of intelligent applications will be deployed at the edge of wireless networks. This trend has generated strong interests in realizing an "intelligent edge" to support AI-enabled applications at various edge devices. Accordingly, a new research area, called edge learning, emerges, which crosses and revolutionizes two disciplines: wireless communication and machine learning. A major theme in edge learning is to overcome the limited computing power, as well as limited data, at each edge device. This is accomplished by leveraging the mobile edge computing (MEC) platform and exploiting the massive data distributed over a large number of edge devices. In such systems, learning from distributed data and communicating between the edge server and devices are two critical and coupled aspects, and their fusion poses many new research challenges. This article advocates a new set of design principles for wireless communication in edge learning, collectively called learning-driven communication. Illustrative examples are provided to demonstrate the effectiveness of these design principles, and unique research opportunities are identified.

Subfields: Computer Networks and Communications

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

Citations in the corpus

Broadband Analog Aggregation for Low-Latency Federated Edge Learning (2018, background): “, edge learning, that concerns training of edge-AI models via computation at edge servers and devices [2]–[4].”
A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges (2022, background): “Zhu et al. [127] presented a new set of design principles for edge learning wireless communication called learning-driven communication.”
Energy Efficient Federated Learning Over Wireless Communication Networks (2019, background): “To implement FL over wireless networks, the wireless devices must transmit their local training results over wireless links [27], which can affect the performance of FL due to limited wireless resources (such as time and bandwidth).”
Distributed Learning in Wireless Networks: Recent Progress and Future Challenges (2021, background): “The authors in [13]–[17] introduced the use of communication techniques to improve the performance of FL algorithms that are implemented over wireless networks.”
Convergence Time Optimization for Federated Learning Over Wireless Networks (2020, background): “In addition, none of these existing works [7]–[18] considers the effect of the local FL models of the users that cannot connect to the BS due to limited wireless resource on the FL convergence time and performance.”
High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning (2020, background): “Among such, several edge learning frameworks such as federated edge learning (FEEL) have been developed based on distributed stochastic gradient descent [2]–[5].”
High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning (2019, background): “by edge devices for artificial intelligence (AI)-model training, several edge learning frameworks such as federated edge learning (FEEL) have been developed based on distributed stochastic gradient descent [1], [2].”
Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning (2020, background): “Therefore, FL becomes a promising technology for distributed data analysis and model training in wireless networks [9], [10], and has been used in many applications, for instance, resource allocation optimization in vehicle-to-vehicle (V2V) communications [11] and content recommendations for smartph”
AI for Next Generation Computing: Emerging Trends and Future Directions (2022, unknown): “12 nclude workload estimation and task scheduling as well as VM consolidation, resource optimisation, and energy conservation [114].”
Semantic-Effectiveness Filtering and Control for Post-5G Wireless Connectivity (2019, background): “, [13]); • Network-layer traffic-based routing: Classify traffic on the basis of its network-level traces and configure routers accordingly to filter out protocol overhead; • Transport-layer semantic-based access and congestion control: Inject data in the network only when relevant and trusted, henc”
Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach (2021, background): “Meanwhile, emerging AI applications also raise new communication problems [12], [13].”
A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art (2019, background): “ation at the edge [358], [359]. On the other hand, edge learning can circumvent drawbacks of cloud AI and on-device AI through the tradeoff between the learning model complexity and the training time [360]. B. Machine Learning for Multi-Access Edge Computing Optimizing MEC face several challenges of”