orion-orion/FedCom
🔬 FedCom为SWPU2022届本科毕业设计《基于社区检测的多任务聚类联邦学习》。本研究提出了一种多任务聚类联邦学习（clustered federated learning, CFL）的新方法，该方法的特点是基于社区检测（community detection）来进行聚类簇的动态划分。
This project helps machine learning practitioners improve model accuracy and training speed when working with federated learning setups, especially when data is distributed heterogeneously across many clients. It takes your existing distributed dataset and model training setup, then intelligently groups clients with similar data patterns. The output is a more accurately trained and faster converging global model.
No commits in the last 6 months.
Use this if you are developing or deploying federated learning models and struggle with accuracy or slow convergence due to diverse data distributions across client devices.
Not ideal if your federated learning setup already achieves high accuracy and fast convergence, or if your clients' data distributions are highly homogeneous.
Stars
69
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/orion-orion/FedCom"
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...