Flower – A Friendly Federated Learning Framework

Re:Flower – A Friendly Federated Learning Framework by riidom on Monday March 28, 2022 @07:05AM (#30829235)

So this is about machine learning apparently, not learning as in teaching students. I don't quite get where the "federated" part comes into play.

[ Parent | on HN ]

Re:Flower – A Friendly Federated Learning Framework by tanto on Monday March 28, 2022 @07:18AM (#30829297)

To quote from Wikipedia:

``` Federated learning (also known as collaborative learning) is a machine learning technique that trains an algorithm across multiple decentralized edge devices or servers holding local data samples, without exchanging them. ```

basically you can train ML models collaboratively without ever seeing the other datasets. One example would be multiple hospitals training models to detect breast cancer without the need to exchange the data samples.

Another example is how Google trains models for the keyboard on Android. See here: https://ai.googleblog.com/2017/04/federated-learning-collabo...

[ Parent | on HN ]

Re:Flower – A Friendly Federated Learning Framework by riidom on Monday March 28, 2022 @07:48AM (#30829474)

Oh thank you, didn't thought it's an official term.

[ Parent | on HN ]