Fact of the Day 1

Share this post

Federated Learning

www.factoftheday1.com

Federated Learning

Source: Google Research Published: April 2017

Danny Sheridan
May 30, 2020
1
Share this post

Federated Learning

www.factoftheday1.com

Source: Google Research
Published: April 2017

Federated Learning

Circulated: May 28, 2020

Federated learning is a machine learning (ML) technique that enables edge devices (e.g., mobile phones) to collaboratively learn a shared prediction model.

How is this different than traditional ML?

Standard ML approaches require centralizing the training data in a datacenter (i.e., the cloud). Federated learning keeps all of your training data on device.

What are the benefits?

Users get increased data privacy, lower latency, and less power consumption for their devices.

How does it work?

  • A user’s device downloads the current ML model from a server.

  • The model is trained on user data stored on their phone.

  • The model is improved. Revisions are sent to the server.

  • The server averages the revisions across many users and applies updates to the model.

  • Repeat.

What’s an example?

Gboard (Google Keyboard) next-word prediction.

Share this post

Federated Learning

www.factoftheday1.com
Comments
TopNewCommunity

No posts

Ready for more?

© 2023 Fact of the Day 1
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing