| 注册
首页|期刊导航|中国工程科学|端云协同智能计算的关键问题、方法和应用

端云协同智能计算的关键问题、方法和应用

张圣宇 况琨 吕承飞 李纪为 肖俊 吴帆 吴飞

中国工程科学2024,Vol.26Issue(1):127-138,12.
中国工程科学2024,Vol.26Issue(1):127-138,12.DOI:10.15302/J-SSCAE-2024.01.011

端云协同智能计算的关键问题、方法和应用

Device-Cloud Collaborative Intelligent Computing:Key Problems,Methods,and Applications

张圣宇 1况琨 2吕承飞 3李纪为 2肖俊 2吴帆 4吴飞5

作者信息

  • 1. 浙江大学软件学院,杭州 310013||浙江大学计算机科学与技术学院,杭州 310013
  • 2. 浙江大学计算机科学与技术学院,杭州 310013
  • 3. 浙江大学计算机科学与技术学院,杭州 310013||淘宝(中国)软件有限公司,杭州 310012
  • 4. 上海交通大学计算机科学与工程系,上海 200240
  • 5. 浙江大学计算机科学与技术学院,杭州 310013||浙江大学上海高等研究院,上海 201203
  • 折叠

摘要

Abstract

Device-cloud collaborative intelligent computing,an emergent result of the development in big data,cloud computing,and edge computing,offers significant improvements in data utilization while protecting user privacy.This approach synergizes the real-time response capabilities of intelligent computing with service robustness.The study explores the application value of this computing paradigm,highlighting technical challenges such as optimizing on-device learning efficiency,mitigating overfitting with limited samples at the device,customizing on-device models,learning false associations under distributional discrepancies,and balancing communication overhead with computational efficiency.We systematically review the progress in mainstream methods within device-cloud collaborative intelligent computing,encompassing efficient computation hardware as the application cornerstone,device-centric collaborative computing,cloud-centric collaborative computing,bidirectional device-cloud collaborative computing,and trustworthy device-cloud collaborative computing.The study also summarizes applications in vertical domains such as recommendation systems,autonomous driving,security systems,and educational models.Looking toward the future of device-cloud collaborative intelligent computing,it underscores the need for focused research on cloud resource application strategies in device model personalization,multi-objective optimization algorithms for device-cloud collaboration,and optimized collaborative strategies between devices and the cloud.

关键词

端云协同/大小模型协同计算/端计算/可信协同/机器学习

Key words

device-cloud collaboration/large and small model collaboration computing/on-device computing/trustworthy collaboration/machine learning

分类

信息技术与安全科学

引用本文复制引用

张圣宇,况琨,吕承飞,李纪为,肖俊,吴帆,吴飞..端云协同智能计算的关键问题、方法和应用[J].中国工程科学,2024,26(1):127-138,12.

基金项目

科技创新2030—"新一代人工智能"重大项目"大小模型端云协同进化与系统"(2022ZD0119100) (2022ZD0119100)

中国工程院咨询项目"新一代人工智能及产业集群发展战略研究"(2022-PP-07) Scientific and Technological Innovation 2030—"New-Generation Artificial Intelligence"Major Project"Co-evolution and System of Small-Large Device-Cloud Model Collaboration"(2022ZD0119100) (2022-PP-07)

Chinese Academy of Engineering project"Strategic Research on New Generation of Artificial Intelligence and Industrial Clusters"(2022-PP-07) (2022-PP-07)

中国工程科学

OA北大核心CSTPCD

1009-1742

访问量0
|
下载量0
段落导航相关论文