A python implementation of a blockchain-based framework of decentralised federated edge learning
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 tec...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/162941 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | 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. |
|---|