Decentralized Federated Learning
This project aims to build a blockchain based decentralized federated learning
Table of Contents
About The Project
Recently, Federated Learning (FL) has gained tremendous traction as it has the ability to provide a privacy-preserving mechanism to train Machine Learning models on hidden data. However, most of today's FL systems are centralized, in which a centralized server is typically used to build the global FL model.
Getting Started
The following instructions will show you how to setup and installed required packages.
Prerequisites
The only requirements is to have python3 and pip installed in your machine.
Installation
-
Download and Install MongoDB Comunity Server from https://www.mongodb.com/try/download/community
-
Clone the repo, move to the project directory
git clone https://github.com/a-dirir/decentralized_FL.git
cd decentralized_FL
Installation for Windows
- Install virtualenv.
py -m pip install --user virtualenv
- Create and activate an environment called dfl
py -m venv dfl
.\dfl\Scripts\activate
- Install python packeges using pip
pip install -r requirements.txt
Installation for Unix/macOs
- Install virtualenv.
python3 -m pip install --user virtualenv
- Create and activate an environment called dfl
python3 -m venv dfl
source dfl/bin/activate
- Install python packeges using pip
pip install -r requirements.txt
Usage
Use this space to show useful examples of how a project can be used. Additional screenshots, code examples and demos work well in this space. You may also link to more resources.
For more examples, please refer to the Documentation
License
Distributed under the MIT License. See LICENSE
for more information.
Contact
Ahmed Mukhtar Dirir - ahmed.m.dirir@gmail.com