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 |

本文概述了联邦学习的主流应用场景,包括Horizontal、Vertical和Transfer Learning,并介绍了Split Learning及其优势与不足。SplitFed是FL与SL的结合,旨在克服两者缺点。文章还探讨了联邦学习中的激励机制和非IID数据问题,并提到了知名平台的相关工作。
最低0.47元/天 解锁文章
1096

被折叠的 条评论
为什么被折叠?



