Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications

Abstract

The thriving of artificial intelligence (AI) applications is driving the further evolution of wireless networks. It has been envisioned that 6G will be transformative and will revolutionize the evolution of wireless from "connected things" to "connected intelligence". However, state-of-the-art deep learning and big data analytics based AI systems require tremendous computation and communication resources, causing significant latency, energy consumption, network congestion, and privacy leakage in both of the training and inference processes. By embedding model training and inference capabilities into the network edge, edge AI stands out as a disruptive technology for 6G to seamlessly integrate sensing, communication, computation, and intelligence, thereby improving the efficiency, effectiveness, privacy, and security of 6G networks. In this paper, we shall provide our vision for scalable and trustworthy edge AI systems with integrated design of wireless communication strategies and decentralized machine learning models. New design principles of wireless networks, service-driven resource allocation optimization methods, as well as a holistic end-to-end system architecture to support edge AI will be described. Standardization, software and hardware platforms, and application scenarios are also discussed to facilitate the industrialization and commercialization of edge AI systems.

arXiv commentThis work is a JSAC invited survey & tutorial paper

References in corpus (65)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• A Brief Survey of Deep Reinforcement Learning
• Millimeter Wave Cellular Wireless Networks: Potentials and Challenges
• The information bottleneck method
• Dynamic Computation Offloading for Mobile-Edge Computing with Energy Harvesting Devices
• Deep Learning Enabled Semantic Communication Systems
• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Towards Federated Learning at Scale: System Design
• QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
• Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
• Manopt, a Matlab toolbox for optimization on manifolds
• Massive Connectivity with Massive MIMO-Part I: Device Activity Detection and Channel Estimation
• TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
• Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
• Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
• Sparse Signal Processing for Grant-Free Massive Connectivity: A Future Paradigm for Random Access Protocols in the Internet of Things
• Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications
• Manifold Mixup: Better Representations by Interpolating Hidden States
• Rate Splitting for MIMO Wireless Networks: A Promising PHY-Layer Strategy for LTE Evolution
• Dynamic Task Offloading and Resource Allocation for Ultra-Reliable Low-Latency Edge Computing
• Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks
• FedML: A Research Library and Benchmark for Federated Machine Learning
• Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
• Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
• Spatial Deep Learning for Wireless Scheduling
• UVeQFed: Universal Vector Quantization for Federated Learning
• Complete Dictionary Recovery over the Sphere I: Overview and the Geometric Picture
• Federated Learning via Intelligent Reflecting Surface
• ATOMO: Communication-efficient Learning via Atomic Sparsification
• Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems
• Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
• On Analog Gradient Descent Learning over Multiple Access Fading Channels
• Split learning for health: Distributed deep learning without sharing raw patient data
• A Field Guide to Federated Optimization
• A Unified Theory of Decentralized SGD with Changing Topology and Local Updates
• Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
• Large-Scale Convex Optimization for Dense Wireless Cooperative Networks
• High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning
• Nomographic Functions: Efficient Computation in Clustered Gaussian Sensor Networks
• Federated Learning Based on Dynamic Regularization
• 6G White Paper on Machine Learning in Wireless Communication Networks
• Learning to Optimize: A Primer and A Benchmark
• Interplay between RIS and AI in Wireless Communications: Fundamentals, Architectures, Applications, and Open Research Problems
• FedSplit: An algorithmic framework for fast federated optimization
• Joint Optimization of Communications and Federated Learning Over the Air
• Robust Group Sparse Beamforming for Multicast Green Cloud-RAN with Imperfect CSI
• Supervised Learning Under Distributed Features
• Data Shuffling in Wireless Distributed Computing via Low-Rank Optimization
• Nonconvex Demixing From Bilinear Measurements
• Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
• Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
• Mathematical Models of Overparameterized Neural Networks
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment
• Consensus Control for Decentralized Deep Learning
• Distributionally Robust Federated Averaging
• Optimized Power Control Design for Over-the-Air Federated Edge Learning
• Distributionally Robust Learning
• A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning
• Fast Convergence Algorithm for Analog Federated Learning
• Neural Calibration for Scalable Beamforming in FDD Massive MIMO with Implicit Channel Estimation
• Delay Analysis of Wireless Federated Learning Based on Saddle Point Approximation and Large Deviation Theory
• Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfer
• Reconfigurable Intelligent Surface for Massive Connectivity
• Over-the-Air Computation via Reconfigurable Intelligent Surface