Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing

2019/05/24 by Zhi Zhou, Xu Chen, Zhou, Zhi +9 · 35 citations
Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Context-Aware Activity Recognition Systems #Distributed #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Networking and Internet Architecture (cs.NI) #Parallel #and Cluster Computing (cs.DC)

paper · pdf · doi:10.48550/arxiv.1905.10083

openalex publication_date 2019/05/24 · openalex created_date 2019/05/29 · openalex updated_date 2026/07/28

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 inter-discipline, edge AI or edge intelligence, is beginning to receive a tremendous amount of interest. However, research on edge intelligence is still in its infancy stage, and a dedicated venue for exchanging the recent advances of edge intelligence is highly desired by both the computer system and artificial intelligence communities. To this end, we conduct a comprehensive survey of the recent research efforts on edge intelligence. Specifically, we first review the background and motivation for artificial intelligence running at the network edge. We then provide an overview of the overarching architectures, frameworks and emerging key technologies for deep learning model towards training/inference at the network edge. Finally, we discuss future research opportunities on edge intelligence. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions and inspire further research ideas on edge intelligence.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ImageNet classification with deep convolutional neural networks
• Neural Architecture Search with Reinforcement Learning
• Efficient Processing of Deep Neural Networks: A Tutorial and Survey
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)

Cited by

• D2M: A Decentralized, Privacy-Preserving, Incentive-Compatible Data Marketplace for Collaborative Learning
• Hyperion: Hierarchical Scheduling for Parallel LLM Acceleration in Multi-tier Networks
• An All-Reduce Compatible Top-K Compressor for Communication-Efficient Distributed Learning
• Prune2Edge: A Multi-Phase Pruning Pipelines to Deep Ensemble Learning in IIoT
• Frustratingly Easy Task-aware Pruning for Large Language Models
• EdgeReasoning: Characterizing Reasoning LLM Deployment on Edge GPUs
• STT-GS: Sample-Then-Transmit Edge Gaussian Splatting with Joint Client Selection and Power Control
• Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons
• Characterizing the Performance of Accelerated Jetson Edge Devices for Training Deep Learning Models
• Layered Architecture for Mobile Intelligence
• Chiplet-Based RISC-V SoC with Modular AI Acceleration
• Joint Memory Frequency and Computing Frequency Scaling for Energy-efficient DNN Inference
• 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
• Cross-stakeholder service orchestration for B5G through capability provisioning
• Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges
• 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
• Machine Learning Systems for Intelligent Services in the IoT: A Survey
• Artificial Intelligence-Enhanced Wearable Blood Pressure Monitoring in Resource-Limited Settings: A Co-Design of Sensors, Model, and Deployment
• 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
• QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference
• Guidelines for the Quality Assessment of Energy-Aware NAS Benchmarks
• SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs
• 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
• CacheFL: Privacy-Preserving and Efficient Federated Cache Model Fine-Tuning for Vision-Language Models
• Federated Learning for Cyber Physical Systems: A Comprehensive Survey

Related

• Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
• Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons
• Artificial Intelligence at the Edge
• Deep Learning in the Era of Edge Computing: Challenges and Opportunities
• Communication-Efficient Edge AI: Algorithms and Systems