ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Communication-Efficient and Attack-Resistant Federated Edge Learning With Dataset Distillation

Zhou, Yanlin; Ma, Xiyao; Wu, Dapeng*; Li, Xiaolin*河北医科大学; 中国科学院
IEEE Transactions on Cloud Computing2023-7DOI: 10.1109/TCC.2022.3215520
17阅读
引用收藏
分享

摘要

Federated Edge Learning considers a large amount of distributed edge nodes collectively train a global gradient-based model for edge computing in the Artificial Internet of Things, which significantly promotes the development of cloud computing. However, current federated learning algorithms take tens of communication rounds transmitting unwieldy model weights under ideal circumstances and hundreds when data is poorly distributed. This drawback directly results in expensive communication overhead for edge devices. Inspired by recent work on dataset distillation and distributed one-shot learning, we propose Distilled One-Shot Federated Learning (DOSFL) to significantly reduce the communication cost while achieving comparable performance. In just one round, each client distills their private dataset, sends the synthetic data to the server, and collectively trains a global model. The distilled data look like noise and are only useful to the specific model weights, i.e., become useless after the model updates. With this weight-less and gradient-less design, the total communication cost of DOSFL is up to three orders of magnitude less than FedAvg while preserving up to 99% performance of centralized training on both vision and language tasks with different models including CNN, LSTM, Transformer, etc. We demonstrate that an eavesdropping attacker cannot properly train a good model using the leaked distilled data, without knowing the initial model weights. DOSFL serves as an inexpensive method to quickly converge on a performant pre-trained model with less than 0.1% communication cost of traditional methods.

学科与关键词

关键词
Communication reductionfederated learningone-shot learningattack
相关
加载中…
  • Byzantine-Resilient Federated Learning at Edge
    Tao, Youming; Cui, Sijia; Xu, Wenlu; Yin, Haofei; Yu, Dongxiao*; Liang, Weifa; Cheng, XiuzhenIEEE Transactions on Computers, 2023, 72(9): 2600-2614.被引 2
  • Efficient Federated Learning for AIoT Applications Using Knowledge Distillation
    Liu, Tian; Xia, Jun; Ling, Zhiwei; Fu, Xin; Yu, Shui; Chen, Mingsong*IEEE Internet of Things Journal, 2023, 10(8): 7229-7243.被引 1
  • A Differentially Private Federated Learning Model Against Poisoning Attacks in Edge Computing
    Zhou, Jun; Wu, Nan; Wang, Yisong; Gu, Shouzhen*; Cao, Zhenfu; Dong, Xiaolei; Choo, Kim-Kwang RaymondIEEE Transactions on Dependable and Secure Computing, 2023, 20(3): 1941-1958.被引 10
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Cloud Computing
发表日期
2023-07
卷期
第 11 卷, 第 3 期
页码
2517-2528
DOI
10.1109/TCC.2022.3215520
成果收录
SCIE

作者

  • Z

    Zhou, Yanlin (第一作者)

  • M

    Ma, Xiyao

查看全部 4 位作者收起作者
  • W

    Wu, Dapeng (通讯)

  • L

    Li, Xiaolin (通讯)

    chinese acad sci · inst med

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417