A python implementation of a blockchain-based framework of decentralised federated edge learning

• Main Author: Tee, Zheng Yang
• Other Authors: Dusit Niyato
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/162941
• Institution: Nanyang Technological University

Federated Learning (FL) is a machine learning technique that allows multiple actors to train a single machine learning model without sharing any local data. This technique is gaining popularity as agencies these days are increasingly concerned about data privacy and security. With blockchain technology, the FL training process could be enhanced in terms of speed, security, and reliability. Therefore, the blockchain federated edge learning (BFEL) is being proposed. Since most research is conducted using Python, this paper aims to introduce an end-to-end BFEL implementation where most of the code can be implemented using Python, instead of Java or other backend languages. We hope that with this demonstration, more researchers will be aware and confident of the current tools to integrate blockchain into their research, thereby improving the adoption of blockchain technology and efficiency of FL.