omarfoq/FedEM

Official code for "Federated Multi-Task Learning under a Mixture of Distributions" (NeurIPS'21)

44
/ 100
Emerging

This project helps machine learning practitioners develop better personalized models for users whose data is stored across many devices and cannot be centrally collected. It takes decentralized datasets (like those from smartphones or IoT devices) as input and outputs custom machine learning models that perform well for each individual client, even if their data patterns are unique. This is for machine learning researchers and engineers working with federated learning setups where data privacy or distribution prevents centralized training.

167 stars. No commits in the last 6 months.

Use this if you need to train personalized machine learning models across many devices without sharing raw data, and existing federated learning methods struggle with diverse user data.

Not ideal if your data can be aggregated into a single location for model training, or if you only need a single model that works for the average user.

federated-learning personalized-machine-learning distributed-training privacy-preserving-ai on-device-intelligence
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

167

Forks

28

Language

Python

License

Apache-2.0

Last pushed

Nov 07, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/omarfoq/FedEM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.