Communication-Efficient Edge AI: Algorithms and Systems

@article{Shi2020CommunicationEfficientEA,
  title={Communication-Efficient Edge AI: Algorithms and Systems},
  author={Yuanming Shi and Kai Yang and Tao Jiang and Jun Zhang and K. Letaief},
  journal={IEEE Communications Surveys \& Tutorials},
  year={2020},
  volume={22},
  pages={2167-2191}
}
Artificial intelligence (AI) has achieved remarkable breakthroughs in a wide range of fields, ranging from speech processing, image classification to drug discovery. This is driven by the explosive growth of data, advances in machine learning (especially deep learning), and the easy access to powerful computing resources. Particularly, the wide scale deployment of edge devices (e.g., IoT devices) generates an unprecedented scale of data, which provides the opportunity to derive accurate models… Expand
Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications
TLDR
This article aims to provide a holistic overview of relevant communication and ML principles and present communication-efficient and distributed learning frameworks with selected use cases. Expand
Communication-Computation Efficient Device-Edge Co-Inference via AutoML
  • Xinjie Zhang, Jiawei Shao, Yuyi Mao, Jun Zhang
  • Computer Science, Engineering
  • ArXiv
  • 2021
Device-edge co-inference, which partitions a deep neural network between a resource-constrained mobile device and an edge server, recently emerges as a promising paradigm to support intelligentExpand
Efficient Low-Latency Dynamic Licensing for Deep Neural Network Deployment on Edge Devices
TLDR
This paper proposes an architecture to solve deploying and processing deep neural networks on edge-devices by leveraging their synergy with the cloud and the access-control mechanisms of the database and allows for dynamic model licensing, which benefits commercial applications. Expand
A Survey on Deep Learning for Challenged Networks: Applications and Trends
Computer networks are dealing with growing complexity, given the everincreasing volume of data produced by all sorts of network nodes. Performance improvements are a non-stop ambition and requireExpand
Energy-Efficient Processing and Robust Wireless Cooperative Transmission for Edge Inference
TLDR
This article presents an energy-efficient edge processing framework to execute deep learning inference tasks at the edge computing nodes whose wireless connections to mobile devices are prone to channel uncertainties and designs a reweighted power minimization approach. Expand
Branchy-GNN: A Device-Edge Co-Inference Framework for Efficient Point Cloud Processing
TLDR
This work proposes Branchy-GNN for efficient graph neural network (GNN) based point cloud processing by leveraging edge computing platforms and employs learning-based joint source-channel coding (JSCC) for the intermediate feature compression to reduce the communication overhead. Expand
Dynamic Workload Allocation for Edge Computing
TLDR
A novel two-stage method to allocate workloads to the server or the edge to maximize inference accuracy under a power constraint and proposes a fine-tuning process to the pretrained model at the edge for achieving better accuracy. Expand
Wireless for Machine Learning
TLDR
An exhaustive review of the state of the art wireless methods that are specifically designed to support Machine Learning services, including over-the-air computation and radio resource allocation optimized for Machine Learning. Expand
Relay-Assisted Cooperative Federated Learning
  • Zehong Lin, Hang Liu, Y. Zhang
  • Computer Science, Engineering
  • ArXiv
  • 2021
TLDR
This paper proposes a relay-assisted cooperative FL scheme to effectively address the straggler issue and deploy multiple half-duplex relays to cooperatively assist the devices in uploading the local model updates to the edge server. Expand
An Energy-Efficient Fine-Grained Deep Neural Network Partitioning Scheme for Wireless Collaborative Fog Computing
TLDR
An energy-efficient fine-grained DNN partitioning scheme for wireless collaborative fog computing systems using the primal-dual decomposition and Lagrange duality theory to minimize the energy consumption. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 240 REFERENCES
Wireless Network Intelligence at the Edge
TLDR
In a first of its kind, this article explores the key building blocks of edge ML, different neural network architectural splits and their inherent tradeoffs, as well as theoretical and technical enablers stemming from a wide range of mathematical disciplines. Expand
Toward an Intelligent Edge: Wireless Communication Meets Machine Learning
TLDR
A new set of design guidelines for wireless communication in edge learning, collectively called learning- driven communication is advocated, which crosses and revolutionizes two disciplines: wireless communication and machine learning. Expand
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
TLDR
A comprehensive survey of the recent research efforts on EI is conducted, which provides an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Expand
Machine Learning at the Network Edge: A Survey
TLDR
This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems. Expand
Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing
TLDR
Eggent is a framework that leverages edge computing for DNN collaborative inference through device-edge synergy and generates the best execution plan through the online change point detection algorithm that maps the current bandwidth state to the optimal configuration. Expand
Broadband Analog Aggregation for Low-Latency Federated Edge Learning
TLDR
This work designs a low-latency multi-access scheme for edge learning based on a popular privacy-preserving framework, federated edge learning (FEEL), and derives two tradeoffs between communication-and-learning metrics, which are useful for network planning and optimization. Expand
Data Shuffling in Wireless Distributed Computing via Low-Rank Optimization
TLDR
An efficient difference-of-convex-functions (DC) algorithm is developed to solve the presented low-rank optimization problem by proposing a novel DC representation for the rank function. Expand
Adaptive Federated Learning in Resource Constrained Edge Computing Systems
TLDR
This paper analyzes the convergence bound of distributed gradient descent from a theoretical point of view, and proposes a control algorithm that determines the best tradeoff between local update and global parameter aggregation to minimize the loss function under a given resource budget. Expand
Neural Networks Meet Physical Networks: Distributed Inference Between Edge Devices and the Cloud
TLDR
This work proposes a distributed DNN architecture that learns end-to-end how to represent the raw sensor data and send it over the network such that it meets the eventual sensing task's needs. Expand
Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning
TLDR
This paper proposes an efficient and flexible 2-step pruning framework for DNN partition between mobile devices and edge servers that can greatly reduce either the wireless transmission workload of the device or the total computation workload. Expand
...
1
2
3
4
5
...