热门标签
热门文章
- 1git无法连接服务器报443错误_443error
- 2mysql inner join 和join_图解MySQL的各种 JOIN，看完不懂来找我！
- 3基于SpringBoot的农产品商城平台_基于springboot+mybatis的绿色果蔬农产品电商平台研究
- 4python实现m3u8转mp4_python m3u8转mp4
- 5nuget.exe安装依赖包举例＜Microsoft.UI.Xaml＞_nuget安装指定框架的包
- 6使用花生壳时，vue前端配置文件启动注意_vue前端配的108.88.3.114启动后108.88.3.1111
- 7Python安装和导入cv库_python import cv
- 8使用Putty PSFTP和C#（开源）和任务计划程序配置来保护FTP或SFTP_putty ftp
- 9基于Android的校园二手闲置物品交易系统设计与实现_校园二手交易平台国内外研究现状
- 10HarmonyOS开发学习笔记_模拟器 unable find the dms service 鸿蒙
当前位置: article > 正文
Federated Learning 联邦学习概述及最新工作_feddefender: client-side attack-tolerant federated
作者：菜鸟追梦旅行 | 2024-03-15 06:30:21
赞
踩
feddefender: client-side attack-tolerant federated learning
声明：以后会逐渐转移到某乎啦，有兴趣的伙伴可以关注：霁月
一、目前主流的联邦学习应用场景
|
|
Cross-silo FL |
Cross-device FL |
| Setting |
Training a model on siloed data. Clients are from different organizations (e.g. medical or financial) or geo-distributed datacenters. |
The clients are a very large number of mobile or IoT (物联网) devices 医疗方面，可能有未来的家庭医生hhh |
| Data distribution |
Data is generated locally and remains decentralized. |
|
| Distribution scale |
Typically 2 - 100 clients. |
Massively parallel, up to 10^10 clients. |
| Addressability |
Each client has an identity or name that allows the system to access it specifically. |
Clients cannot be indexed directly (i.e., no use of client identifiers). 不知道哪些数据已经收集，有重复手机训练的可能性 |
| Data partition axis |
Partition is fixed. Could be horizonta |
|
推荐阅读
相关标签
