EricLoong/feddip

The official code for ICDM2023 paper: ' FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization'

21
/ 100
Experimental

This project helps machine learning engineers improve the efficiency of federated learning models. It takes distributed datasets and model architectures like AlexNet or ResNet, then applies dynamic pruning and incremental regularization to produce a more lightweight yet accurate global model. Data scientists and ML researchers working with privacy-sensitive or large-scale distributed data would use this.

No commits in the last 6 months.

Use this if you are developing or experimenting with federated learning systems and need to optimize model size and training performance without sacrificing accuracy, especially for image classification tasks.

Not ideal if you are looking for a general-purpose federated learning framework that does not prioritize model compression or pruning.

federated-learning model-optimization distributed-machine-learning deep-learning-compression computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

MIT

Last pushed

Aug 16, 2024

Commits (30d)

0

Get this data via API

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

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