arodio/CA-Fed
Official code for "Federated Learning under Heterogeneous and Correlated Client Availability" (INFOCOM'23)
This project helps machine learning engineers and researchers train models more effectively using federated learning, especially when data is spread across many mobile or IoT devices with inconsistent availability. It takes in local datasets from various clients and outputs a collaboratively trained machine learning model. The ideal user is someone building or experimenting with federated learning systems where client participation is unreliable and correlated.
No commits in the last 6 months.
Use this if you are developing or deploying federated learning models and need to manage challenges arising from devices frequently going offline or having inconsistent data contribution, which can slow down training or bias your model.
Not ideal if your federated learning clients are always available and have perfectly stable network connections, or if you are not working with federated learning at all.
Stars
29
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/arodio/CA-Fed"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
flwrlabs/flower
Flower: A Friendly Federated AI Framework
JonasGeiping/breaching
Breaching privacy in federated learning scenarios for vision and text
zama-ai/concrete-ml
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on...
anupamkliv/FedERA
FedERA is a modular and fully customizable open-source FL framework, aiming to address these...
p2pfl/p2pfl
P2PFL is a decentralized federated learning library that enables federated learning on...