Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
2019/06/12 by Zhi Zhou, Xu Chen, En Li +3 · 2,238 citations
Computer Science · #Advanced Neural Network Applications #Applications of artificial intelligence #Artificial intelligence #Big data #Cloud computing #Computer science #Data mining #Data science #Deep learning #Edge computing #Edge device #Enhanced Data Rates for GSM Evolution #IoT and Edge/Fog Computing #Mobile edge computing #Multimedia #Privacy-Preserving Technologies in Data #The Internet #World Wide Web
paper · pdf · doi:10.1109/jproc.2019.2918951
published in Proceedings of the IEEE 107(8), 1738-1762 (Institute of Electrical and Electronics Engineers)
openalex publication_date 2019/06/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
Abstract
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.
Citations
Cited by
- CRIME: Input-Dependent Collaborative Inference for Recurrent Neural Networks
- Scalable Explainability-as-a-Service (XaaS) for Edge AI Systems
- A Self-Calibrating Agentic AI Framework for Autonomous Edge Resource Allocation
- Task-Oriented Communication with Hybrid-Precision Models
- Data Efficient Any Transformer-to-Mamba Distillation via Attention Bridge
- Deep Learning Anomaly Detection for Cellular IoT With Applications in Smart Logistics
- Client-Based Intelligence for Resource Efficient Vehicular Big Data Transfer in Future 6G Network
- Gradient Statistics Aware Power Control for Over-the-Air Federated Learning
- D2M: A Decentralized, Privacy-Preserving, Incentive-Compatible Data Marketplace for Collaborative Learning
- A Content Driven Resource Allocation Scheme for Video Transmission in Vehicular Networks
- When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multi-Timescale Resource Management for Multi-access Edge Computing in 5G Ultra Dense Network
- Hyperion: Hierarchical Scheduling for Parallel LLM Acceleration in Multi-tier Networks
- Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control
- Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
- An All-Reduce Compatible Top-K Compressor for Communication-Efficient Distributed Learning
- Federated Learning in Mobile Edge Networks: A Comprehensive Survey
- Sparse Optimization for Green Edge AI Inference
- On-Device Machine Learning: An Algorithms and Learning Theory Perspective
- Leveraging the Power of Prediction: Predictive Service Placement for Latency-Sensitive Mobile Edge Computing
- Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
- Integrated 3C in NOMA-enabled Remote-E-Health Systems
- Towards Self-learning Edge Intelligence in 6G
- Frustratingly Easy Task-aware Pruning for Large Language Models
- EdgeReasoning: Characterizing Reasoning LLM Deployment on Edge GPUs
- An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee
- STT-GS: Sample-Then-Transmit Edge Gaussian Splatting with Joint Client Selection and Power Control
- Deep Reinforcement Learning for Delay-Oriented IoT Task Scheduling in Space-Air-Ground Integrated Network
- CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices
- Optimizing AI Service Placement and Resource Allocation in Mobile Edge Intelligence Systems
- Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons
- Embedding artificial intelligence in society: looking beyond the EU AI master plan using the culture cycle
- Characterizing the Performance of Accelerated Jetson Edge Devices for Training Deep Learning Models
- Energy-Efficient Processing and Robust Wireless Cooperative Transmission for Edge Inference
- Layered Architecture for Mobile Intelligence
- EC-SAGINs: Edge Computing-enhanced Space-Air-Ground Integrated Networks for Internet of Vehicles
- Dynamic DNN Decomposition for Lossless Synergistic Inference
- Deploying Federated Learning in Large-Scale Cellular Networks: Spatial Convergence Analysis
- Wireless for Machine Learning
- Chiplet-Based RISC-V SoC with Modular AI Acceleration
- Joint Memory Frequency and Computing Frequency Scaling for Energy-efficient DNN Inference
- Crowd-MECS: A Novel Crowdsourcing Framework for Mobile Edge Caching and Sharing
- A Federated Fine-Tuning Paradigm of Foundation Models in Heterogenous Wireless Networks
- Self-Organising Memristive Networks as Physical Learning Systems
- Toward Edge General Intelligence with Agentic AI and Agentification: Concepts, Technologies, and Future Directions
- DeepCP: Deep Learning Driven Cascade Prediction Based Autonomous Content Placement in Closed Social Network
- Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges
- Knowledge Distillation for Mobile Edge Computation Offloading
- Adaptive In-network Collaborative Caching for Enhanced Ensemble Deep Learning at Edge
- Adaptive AI Agent Placement and Migration in Edge Intelligence Systems
- Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts
- Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models
- From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices
- Learning Centric Wireless Resource Allocation for Edge Computing: Algorithm and Experiment
- Artificial Intelligence-Enhanced Wearable Blood Pressure Monitoring in Resource-Limited Settings: A Co-Design of Sensors, Model, and Deployment
- Intelligent Sensing Scheduling for Mobile Target Tracking Wireless Sensor Networks
- Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design
- Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfer
- 6G Internet of Things: A Comprehensive Survey
- Physical Intelligence on the Edge: A Vision for the Decade Ahead
- Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning
- The AnyLog Edge Data Fabric
- Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees
- WSCoach: Wearable Real-time Auditory Feedback for Reducing Unwanted Words in Daily Communication
- Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges
- Communication-Computation Trade-Off in Resource-Constrained Edge Inference
- A Comprehensive Overview on 5G-and-Beyond Networks with UAVs: From Communications to Sensing and Intelligence
- QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference
- Communication-Efficient Edge AI Inference Over Wireless Networks
- Machine Intelligence at the Edge with Learning Centric Power Allocation
- HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learning
- 6G White Paper on Edge Intelligence
- HierTrain: Fast Hierarchical Edge AI Learning with Hybrid Parallelism in Mobile-Edge-Cloud Computing
- CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learning
- Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework
- An Overview on Multiway Relay Communications: Fundamental Issues, Recent Advances, and New Challenges
- Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence
- AI in knowledge sharing, which ethical challenges are raised in decision-making processes for organisations?
- Guidelines for the Quality Assessment of Energy-Aware NAS Benchmarks
- SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs
- Management of Resource at the Network Edge for Federated Learning
- Creating Robust Deep Neural Networks With Coded Distributed Computing for IoT Systems
- HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference
- A Survey on Open-Source Edge Computing Simulators and Emulators: The Computing and Networking Convergence Perspective
- Chisme: Heterogeneity-Aware Gossip Learning
- Reconfigurable Intelligent Surface Assisted Edge Machine Learning
- An Edge Computing-based Photo Crowdsourcing Framework for Real-time 3D Reconstruction
- CacheFL: Privacy-Preserving and Efficient Federated Cache Model Fine-Tuning for Vision-Language Models
- Federated Learning for Cyber Physical Systems: A Comprehensive Survey
- From Semantic Communication to Semantic-aware Networking: Model, Architecture, and Open Problems
- LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition
- Real-Time AI Service Economy: A Framework for Agentic Computing Across the Continuum
- LODAP: On-Device Incremental Learning Via Lightweight Operations and Data Pruning
- Computation-Bandwidth-Memory Trade-offs: A Unified Paradigm for AI Infrastructure
- TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction
- Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
- Scalable and Communication-efficient Decentralized Federated Edge Learning with Multi-blockchain Framework
- Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with Heterogeneous Learning Tasks
- Distributed Artificial Intelligence-as-a-Service (DAIaaS) for Smarter IoE and 6G Environments. [europepmc]
- Model-size reduction for reservoir computing by concatenating internal states through time. [europepmc]
- Dynamic Inference Approach Based on Rules Engine in Intelligent Edge Computing for Building Environment Control. [europepmc]
- Camera-LiDAR Multi-Level Sensor Fusion for Target Detection at the Network Edge. [europepmc]
- Memristor-CMOS Hybrid Neuron Circuit with Nonideal-Effect Correction Related to Parasitic Resistance for Binary-Memristor-Crossbar Neural Networks. [europepmc]
- Green IoT and Edge AI as Key Technological Enablers for a Sustainable Digital Transition towards a Smart Circular Economy: An Industry 5.0 Use Case. [europepmc]
- Federated Learning in Edge Computing: A Systematic Survey. [europepmc]
- Impact of Asymmetric Weight Update on Neural Network Training With Tiki-Taka Algorithm. [europepmc]
- Imtidad: A Reference Architecture and a Case Study on Developing Distributed AI Services for Skin Disease Diagnosis over Cloud, Fog and Edge. [europepmc]
- A Systematic Literature Review on Distributed Machine Learning in Edge Computing. [europepmc]
- Real-Time Fault Detection and Condition Monitoring for Industrial Autonomous Transfer Vehicles Utilizing Edge Artificial Intelligence. [europepmc]
- Prediction of Glucose Concentration in Children with Type 1 Diabetes Using Neural Networks: An Edge Computing Application. [europepmc]
- Lead federated neuromorphic learning for wireless edge artificial intelligence. [europepmc]
- Multi-Model Running Latency Optimization in an Edge Computing Paradigm. [europepmc]
- Multi-Agent Multi-View Collaborative Perception Based on Semi-Supervised Online Evolutive Learning. [europepmc]
- Leveraging IoT-Aware Technologies and AI Techniques for Real-Time Critical Healthcare Applications. [europepmc]
- A Survey on Optimization Techniques for Edge Artificial Intelligence (AI). [europepmc]
- At the Confluence of Artificial Intelligence and Edge Computing in IoT-Based Applications: A Review and New Perspectives. [europepmc]
- Autonomous Vehicles Enabled by the Integration of IoT, Edge Intelligence, 5G, and Blockchain. [europepmc]
- Integration of neuromorphic AI in event-driven distributed digitized systems: Concepts and research directions. [europepmc]
- Boosting precision crop protection towards agriculture 5.0 via machine learning and emerging technologies: A contextual review. [europepmc]
- A Faster and Lighter Detection Method for Foreign Objects in Coal Mine Belt Conveyors. [europepmc]
- Continuous Process Verification 4.0 application in upstream: adaptiveness implementation managed by AI in the hypoxic bioprocess of the Pichia pastoris cell factory. [europepmc]
- Towards fairness-aware and privacy-preserving enhanced collaborative learning for healthcare. [europepmc]
- Artificial Intelligence-Enhanced Wearable Blood Pressure Monitoring in Resource-Limited Settings: A Co-Design of Sensors, Model, and Deployment. [europepmc]
Related