What the project does
This project focuses on implementing a federated learning system for artificial intelligence (AI) models. Federated learning is a distributed model training approach where multiple nodes or clients collaborate to train a global model without sharing their raw data. By using this methodology, nodes can collaborate to improve the global model without compromising the privacy of their data.
Additionally, this project aims to achieve interoperability across different networks using Chainlink's Cross-Chain Interoperability Protocol (CCIP). This allows nodes on different networks to collaborate in training and inferring the AI model, which is essential for effective and efficient collaboration in a decentralized environment.
Show me the code!
repo fate_backend file heteroLRPredictV2.py line 120-121
repo blockchain_dev_kit file startSCConnection.py line 242-288
Smart contract deployed (https://sepolia.etherscan.io/address/0xF6dace8A66Cfc8E86D314fB61b29583EC67B9347)
Challenges we ran into
Trying to intercommunicate with different blockchains through CCIP using our own token.