swagshaw/awesome-cloud-edge-ai

A curated list of research in System for Edge Intelligence and Computing(Edge MLSys), including Frameworks, Tools, Repository, etc. Paper notes are also provided.

Hi there, I'm Yang! 👋

Welcome to my GitHub. I'm Yang Xiao(肖扬) or you can call me Austin (ChatGPT gave me this English name). I research speech and audio for the Fortemedia. Before that I graduated as the Master of Artificial Intelligence at Nanyang Technological University. My research lies at building efficient, robust, data-centric machine learning system. At this moment, I mainly work in the data-centric speech system that are continual, real-time and efficient.

• 📫 How to reach me: [Email], [LinkedIn], [Homepage].

awesome-cloud-edge-ai's Issues

Segmentation of DL Models(Cloud-Edge Collaborative Inference)

Likes Neurosurgeon
the model can be segmented into multiple partitions and then allocated to:

1. distributed edge nodes
   A Locally Distributed Mobile Computing Framework for DNN based Android Applications
   https://readpaper.com/paper/2896769682
   DeepThings: Distributed Adaptive Deep Learning Inference on Resource-Constrained IoT Edge Clusters

Task Scheduling with Optimized Transmission Time in Collaborative Cloud-Edge Learning(Cloud-Edge Collaborative Training)

https://readpaper.com/paper/2896070538

Cloud-Edge Training(Cloud-Edge Collaborative Training)

Task Scheduling with Optimized Transmission Time in Collaborative Cloud-Edge Learning
https://readpaper.com/paper/2896070538

DL for Adaptive Edge Caching(Edge-Caching for Sharing of DL Computation)

Hierarchical Edge Caching in Device-to-Device Aided Mobile Networks: Modeling, Optimization, and Design
https://readpaper.com/paper/2806446964
DeepCachNet: A Proactive Caching Framework Based on Deep Learning in Cellular Networks
https://readpaper.com/paper/2911717124
Deep learning-based edge caching for multi-cluster heterogeneous networks
https://readpaper.com/paper/2918093752
Learn to Cache: Machine Learning for Network Edge Caching in the Big Data Era
https://readpaper.com/paper/2833256931
Deep Learning Based Caching for Self-Driving Car in Multi-access Edge Computing
https://readpaper.com/paper/2895666646
A smart caching mechanism for mobile multimedia in information centric networking with edge computing
https://readpaper.com/paper/2885965464

Sharing of DL Computation(Edge-Caching for Sharing of DL Computation)

Cachier: Edge-Caching for Recognition Applications
https://readpaper.com/paper/2736071714
DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications
https://readpaper.com/paper/2626129225
DeepCache: Principled Cache for Mobile Deep Vision
https://readpaper.com/paper/2889402930
FoggyCache: Cross-Device Approximate Computation Reuse
https://readpaper.com/paper/2896985569
Mainstream: dynamic stem-sharing for multi-tenant video processing
https://readpaper.com/paper/2885829265

Real-time Video&Audio Analytic based on edge and cloud intelligence

• Distributed and Efficient Object Detection in Edge Computing: Challenges and Solutions
• https://readpaper.com/paper/2797952247
• A New Deep Learning-Based Food Recognition System for Dietary Assessment on An Edge Computing Service Infrastructure
• https://readpaper.com/paper/2585425668
• DeepCham: Collaborative Edge-Mediated Adaptive Deep Learning for Mobile Object Recognition
• https://readpaper.com/paper/2560645261
• NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision
• https://readpaper.com/paper/3103203826
• LAVEA: Latency-Aware Video Analytics on Edge Computing Platform
• https://readpaper.com/paper/2736305332
• EdgeEye: An Edge Service Framework for Real-time Intelligent Video Analytics
• https://readpaper.com/paper/2807214292
• Smart Surveillance as an Edge Network Service: From Harr-Cascade, SVM to a Lightweight CNN
• https://readpaper.com/paper/2963046229
• VideoEdge: Processing Camera Streams using Hierarchical Clusters
• https://readpaper.com/paper/2896225285

Federated Sensing: Edge-Cloud Elastic Collaborative Learning for Intelligent Sensing(Cloud-Edge Collaborative Training)

https://ieeexplore.ieee.org/document/9328824

CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learning(Selection and Optimization of DL Models in Edge)

https://arxiv.org/abs/2005.02177

Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

https://readpaper.com/paper/2949701228

DL Model Selection(Selection and Optimization of DL Models in Edge)

Adaptive deep learning model selection on embedded systems
https://readpaper.com/paper/2797932837
AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles
https://arxiv.org/abs/2006.04432

Optimization of DL Models in Edge(Selection and Optimization of DL Models in Edge)