.png){kind=icon}
返回
Differentially private knowledge transfer for federated learning
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-023-38794-x.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Extracting useful knowledge from big data is important for machine learning. When data is privacy-sensitive and cannot be directly collected, federated learning is a promising option that extracts knowledge from decentralized data by learning and exchanging model parameters, rather than raw data. However, model parameters may encode not only non-private knowledge but also private information of local data, thereby transferring knowledge via model parameters is not privacy-secure. Here, we present a knowledge transfer method named PrivateKT, which uses actively selected small public data to transfer high-quality knowledge in federated learning with privacy guarantees. We verify PrivateKT on three different datasets, and results show that PrivateKT can maximally reduce 84% of the performance gap between centralized learning and existing federated learning methods under strict differential privacy restrictions. PrivateKT provides a potential direction to effective and privacy-preserving knowledge transfer in machine intelligent systems. To ensure the privacy of processed data, federated learning approaches involve local differential privacy techniques which however require communicating a large amount of data that needs protection. The authors propose here a framework that uses selected small data to transfer knowledge in federated learning with privacy guarantees.
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
15.7
论文数:
9.3W
被引数:
91.2W
机构
引用论文
Ionic liquids derived from trialkylsulfonium bromides: Physicochemical properties and potential applications溴化三烷基锍衍生的离子液体: 物理化学性质和潜在应用
PREAI
分享收藏Machine learning reveals cryptic dialects that explain mate choice in a songbird.png)
NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏分享收藏Stratification of hospitalized COVID-19 patients into clinical severity progression groups by immuno-phenotyping and machine learningNATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏The Ada protein acts as both a positive and a negative modulator of Escherichia coli's response to methylating agents.Ada蛋白充当大肠杆菌对甲基化试剂的反应的阳性和阴性调节剂。OAAI
OAAI分享收藏
查看更多内容