大数据 ›› 2024, Vol. 10 ›› Issue (3): 40-54.doi: 10.11959/j.issn.2096-0271.2024032

• 专题:政务数据处理 • 上一篇    下一篇

基于联邦学习的政务大数据平台应用研究

吴坚平1, 陈超超1, 金加和2,3, 吴春明1   

  1. 1 浙江大学计算机科学与技术学院,浙江 杭州 310027
    2 浙江省大数据发展中心,浙江 杭州 310007
    3 浙江省数据开放融合关键技术研究重点实验室,浙江 杭州 310007
  • 出版日期:2024-05-01 发布日期:2024-05-01
  • 作者简介:吴坚平(1983- ),男,浙江大学计算机科学与技术学院博士生,主要研究方向为联邦学习、公共数据安全、推荐系统。
    陈超超(1988- ),男,博士,浙江大学计算机科学与技术学院特聘研究员、博士生导师,主要研究方向为隐私保护机器学习、分布式机器学习、图机器学习和推荐系统等。
    金加和(1965- ),男,浙江省数据开放融合关键技术研究重点实验室副主任,浙江省大数据发展中心主任、正高级工程师,浙江省政务服务标准化技术委员会副秘书长。主要研究方向为数字政府、公共数据融合应用、数据治理、隐私计算等。
    吴春明(1967- ),男,浙江大学系统结构与网络安全研究所副所长、教授、博士生导师,主要研究方向为新型网络体系结构、软件定义网络、工业互联网内生安全等。
  • 基金资助:
    浙江省“尖兵”“领雁”研发攻关计划项目(2022C01243)

Research on the application of government big data platform based on federated learning

Jianping WU1, Chaochao CHEN1, Jiahe JIN2,3, Chunming WU1   

  1. 1 College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
    2 Big Data Development Center of Zhejiang Province, Hangzhou 310007, China
    3 Key Laboratory of Key Technologies for Open Data Fusion in Zhejiang Province, Hangzhou 310007, China
  • Online:2024-05-01 Published:2024-05-01
  • Supported by:
    Research and Development Plan Project for “Top Soldiers” and “Leading Wild Goose” in Zhejiang Province(2022C01243)

摘要:

当前数字政府建设已进入深水区,政务大数据平台作为数据底座支撑各类政务信息化应用,其隐私数据的安全性和合规性一直被业界广泛关注。联邦学习是一类解决数据孤岛的重要方法,基于联邦学习的政务一体化大数据平台应用具有较高的研究价值。首先,介绍政务大数据平台及联邦学习应用现状;然后,分析政务大数据平台面临的隐私数据的采集、分类分级、共享三大管理挑战;接着,阐述基于联邦学习的推荐算法和隐私集合求交技术的解决方法;最后,对政务大数据平台隐私数据的未来应用进行了总结和展望。

关键词: 政务大数据, 联邦学习, 推荐算法, 隐私集合求交

Abstract:

At present, the construction of digital government has entered a deepwater area.The government big data platform, as a data base, supports various government information applications.The security and compliance of its private data has been widely concerned by the industry.Federated learning is an important method to effectively solve data silos, and the application of government big data platforms based on federated learning has high research value.Firstly, the current status of government big data platforms and its federated learning application were introduced.Then this paper analyzed three major management challenges involved in the collection, classification and grading and sharing of privacy data on government big data platforms.Further, the problem-solving methods of federated learning based recommendation algorithms and privacy intersection techniques were explored.Finally, summaries and prospects were made for the future application of privacy data on government big data platforms.

Key words: government big data, federated learning, recommendation algorithm, private set intersection

中图分类号: 

No Suggested Reading articles found!