Edge Intelligence: Architectures, Challenges, and Applications
arXiv:2003.12172
Abstract
Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis in locations close to where data is captured based on artificial intelligence. The aim of edge intelligence is to enhance the quality and speed of data processing and protect the privacy and security of the data. Although recently emerged, spanning the period from 2011 to now, this field of research has shown explosive growth over the past five years. In this paper, we present a thorough and comprehensive survey on the literature surrounding edge intelligence. We first identify four fundamental components of edge intelligence, namely edge caching, edge training, edge inference, and edge offloading, based on theoretical and practical results pertaining to proposed and deployed systems. We then aim for a systematic classification of the state of the solutions by examining research results and observations for each of the four components and present a taxonomy that includes practical problems, adopted techniques, and application goals. For each category, we elaborate, compare and analyse the literature from the perspectives of adopted techniques, objectives, performance, advantages and drawbacks, etc. This survey article provides a comprehensive introduction to edge intelligence and its application areas. In addition, we summarise the development of the emerging research field and the current state-of-the-art and discuss the important open issues and possible theoretical and technical solutions.
arXiv comment53 pages, 37 figures, survey
References in corpus (91)
- Distilling the Knowledge in a Neural Network
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Deep Learning with Differential Privacy
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- A Tractable Approach to Coverage and Rate in Cellular Networks
- Federated Learning: Strategies for Improving Communication Efficiency
- MobileNetV2: Inverted Residuals and Linear Bottlenecks
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- FitNets: Hints for Thin Deep Nets
- Federated Learning with Non-IID Data
- Neural Architecture Search: A Survey
- Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- Federated Learning for Mobile Keyboard Prediction
- In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- Compressing Deep Convolutional Networks using Vector Quantization
- Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
- A Survey on Mobile Edge Networks: Convergence of Computing, Caching and Communications
- Towards Federated Learning at Scale: System Design
- DeepID3: Face Recognition with Very Deep Neural Networks
- Robust dynamic classes revealed by measuring the response function of a social system
- How To Backdoor Federated Learning
- Learning Differentially Private Recurrent Language Models
- Poisoning Attacks against Support Vector Machines
- Secure Federated Transfer Learning
- Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
- Revisiting Distributed Synchronous SGD
- Federated Optimization:Distributed Optimization Beyond the Datacenter
- Compressing Neural Networks with the Hashing Trick
- Speeding up Convolutional Neural Networks with Low Rank Expansions
- Ensembles of Deep LSTM Learners for Activity Recognition using Wearables
- Differentially Private Federated Learning: A Client Level Perspective
- Caching at the Wireless Edge: Design Aspects, Challenges and Future Directions
- Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications
- Optimal Geographic Caching In Cellular Networks
- Applied Federated Learning: Improving Google Keyboard Query Suggestions
- Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks
- Distributed Learning in Wireless Sensor Networks
- Mitigating Sybils in Federated Learning Poisoning
- Hello Edge: Keyword Spotting on Microcontrollers
- A Crowdsourcing Framework for On-Device Federated Learning
- CryptoDL: Deep Neural Networks over Encrypted Data
- Federated Meta-Learning with Fast Convergence and Efficient Communication
- Wireless Content Caching for Small Cell and D2D Networks
- Mobility-Aware Caching for Content-Centric Wireless Networks: Modeling and Methodology
- Data-Free Knowledge Distillation for Deep Neural Networks
- A Survey on Neural Architecture Search
- BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning
- SecureBoost: A Lossless Federated Learning Framework
- Federated Learning for Emoji Prediction in a Mobile Keyboard
- Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
- Neural Networks with Few Multiplications
- Federated Learning in Mobile Edge Networks: A Comprehensive Survey
- Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent
- 6G White Paper on Edge Intelligence
- Fundamentals of Cluster-Centric Content Placement in Cache-Enabled Device-to-Device Networks
- Federated Multi-Task Learning
- Abnormal Client Behavior Detection in Federated Learning
- Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks
- Federated Learning Of Out-Of-Vocabulary Words
- Deep Model Compression: Distilling Knowledge from Noisy Teachers
- Moonshine: Distilling with Cheap Convolutions
- Optimal Caching and Scheduling for Cache-enabled D2D Communications
- Federated Deep Reinforcement Learning
- Optimizing Performance of Recurrent Neural Networks on GPUs
- Distributed Deep Neural Networks over the Cloud, the Edge and End Devices
- NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
- Automated Pruning for Deep Neural Network Compression
- Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy
- FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare
- DeepIoT: Compressing Deep Neural Network Structures for Sensing Systems with a Compressor-Critic Framework
- Stochastic, Distributed and Federated Optimization for Machine Learning
- Musical Chair: Efficient Real-Time Recognition Using Collaborative IoT Devices
- SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis
- Cooperative Device-to-Device Communications With Caching
- Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation
- DEEProtect: Enabling Inference-based Access Control on Mobile Sensing Applications
- DeepRT: deep learning for peptide retention time prediction in proteomics
- MobiCacher: Mobility-Aware Content Caching in Small-Cell Networks
- LEP-CNN: A Lightweight Edge Device Assisted Privacy-preserving CNN Inference Solution for IoT
- Fingerprinting Smart Devices Through Embedded Acoustic Components
- Fast and Energy-Efficient CNN Inference on IoT Devices
- Science Driven Innovations Powering Mobile Product: Cloud AI vs. Device AI Solutions on Smart Device
- Cache-enabled Heterogeneous Cellular Networks: Comparison and Tradeoffs
- Deep Learning Towards Mobile Applications
- On the efficient representation and execution of deep acoustic models
- Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices
- DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning
- Knowledge is at the Edge! How to Search in Distributed Machine Learning Models
Cited by in corpus (11)
- AI based Service Management for 6G Green Communications
- Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
- 6G White Paper on Edge Intelligence
- Incentive Mechanism Design for Resource Sharing in Collaborative Edge Learning
- COVID-19 Imaging Data Privacy by Federated Learning Design: A Theoretical Framework
- Jack and Masters of all Trades: One-Pass Learning Sets of Model Sets From Large Pre-Trained Models
- Software Engineering Approaches for TinyML based IoT Embedded Vision: A Systematic Literature Review
- System Intelligence for UAV-Based Mission Critical with Challenging 5G/B5G Connectivity
- State-of-the-art Techniques in Deep Edge Intelligence
- Management of Resource at the Network Edge for Federated Learning
- Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design