Flower: A Friendly Federated Learning Framework
-
Updated
May 23, 2024 - Python
Flower: A Friendly Federated Learning Framework
HeFlwr: Federated Learning for Heterogeneous Devices
A simple tool to perform Federated Learning on various models and datasets.
Comparing centralised machine learning and federated learning using flower framework. Building a custom strategy over the base FedAvg called FedCustom which has a higher learning rate and several other hyper parameters to increase the accuracy.
This is a simple demonstration of how MLflow can be utilised to track and trace local ML models trained in a Federated Learning set-up.
BookingService
This project utilizes federated learning with XGBoost for early cardiovascular disease detection, ensuring data privacy through Federated XGBoost Bagging. Built on the Flower architecture, it enables collaborative model training across decentralized healthcare datasets.
Collect/process data via various data sources : website / js website / API. Run scrapping pipeline via Celery, and Travis cron task. Dump the scraped data to slack
Full stack, modern web application generator. Using FastAPI, MongoDB as database, Docker, automatic HTTPS and more.
This is the repository for the Djinni-Clone-API project, which is a clone of the Djinni web service. This API implements a basic set of functionalities allowing users to interact with the platform.
Experiments on MNIST dataset and federated training using Flower framework
API user authentication.
Resource-Adaptive Federated Learning Tool
Github Pages
Add a description, image, and links to the flower topic page so that developers can more easily learn about it.
To associate your repository with the flower topic, visit your repo's landing page and select "manage topics."