omarfoq/knn-per
Official code for "Personalized Federated Learning through Local Memorization" (ICML'22)
This project helps machine learning practitioners develop and evaluate personalized federated learning models. It takes distributed datasets, like images or text from various clients, and produces custom-tailored models for each client while still benefiting from shared knowledge across all participants. This is ideal for data scientists or ML engineers building systems where data privacy and personalization are critical.
No commits in the last 6 months.
Use this if you need to train machine learning models collaboratively across many clients, where each client has unique data characteristics and requires a personalized model rather than a single global model.
Not ideal if your clients' data distributions are very similar, or if you only need a single, generalized model for all users.
Stars
44
Forks
16
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/omarfoq/knn-per"
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...