FELToken is connecting owners of the data with scientists to train their machine learning models while preserving the privacy of the data. Current federated learning solutions rely on a central server. We are building a product with the simplest user experience possible while being decentralized. This allows anonymous participation of data providers and prevents malicious activities. Data providers get rewards for sharing their data and resulting models can be further sold. Exchange of all models is encrypted so only authorized parties can use the model. We would like to further improve our tool by connecting with Ocean infrastructure.
Platform for a decentralized and more secure solution for federated learning while anonymizing data providers. Allowing data scientists to do machine learning on decentralized data without compromising its privacy.
- GitHub: Breta01 (Břetislav Hájek) · GitHub
- LinkedIn: https://www.linkedin.com/in/břetislav-hájek-75167111b
- GitHub: FilipMasar (Filip Masar) · GitHub
- LinkedIn: https://www.linkedin.com/in/filip-masar-776a0a174/
- Kernel KB4 fellow https://kernel.community/
- Co-founder at http://avtr.gg/
- Front-end developer at https://avast.com/
FELToken [Round 15]
Using federated learning to train machine learning models across multiple datasets while preserving privacy using compute-to-data on Ocean marketplace.
The final product of FELToken is a platform for running machine learning across distributed data sets without compromising the privacy of the data. We already have our tool for running data provider clients and web applications for managing the projects. Now we would like to integrate it with the Ocean protocol. With Ocean integration, users will be able to use data already published on the Ocean marketplace using the compute-to-data. This would add an extra layer of functionalities over the ocean protocol. We would also like to add the possibility of further selling trained models through Ocean.
During development, we focus mainly on making the process of setting up the federated learning project as simple as possible. So that data scientists and interested parties can train their models without any extra knowledge about smart contracts and blockchain. Once the core components are working there are many possible ways for further extension. The tool can also act as a platform for further federated learning research.
- Using compute-to-data with FELToken client code (at least some dome version)
- Script for publishing data on Ocean (for selling models and easily integrating our web application with ocean)
- Redesign application (for better UX)
- Write blog post about our experience and progress with Ocean
We already finished the first release (MVP, video walkthrough: https://youtu.be/uoBl2yeO7hY). It demonstrates the core functionalities and everyone can try it. We will continue working on more improvements and extensions. We are especially interested in using Ocean’s compute-to-data solution which could replace our data provider code. We want to start working on integrating compute-to-data over the next month. This would allow seamless integration with Ocean marketplace.
Ocean marketplace integration will be a win-win situation for us and the Ocean. Our tool would add an extra analytics layer on top of the Ocean marketplace. Allowing users to derive useful statistics or train machine learning on their data. And we will be able to attract more users who already use the ocean for storing their data. With Ocean integration, we might bring even more users interested in machine learning to Ocean.