Democratizing Federated Learning with Blockchain and Multi-Task Peer Prediction

TL;DR

This paper proposes a decentralized federated learning framework using blockchain and multi-task peer prediction, leveraging smart contracts and incentives to address computational and storage challenges.

Contribution

It introduces a novel approach combining blockchain and peer prediction to decentralize AI training and incentivize participant contributions.

Findings

Utilizes smart contracts and cryptocurrencies for incentivization.

Addresses blockchain's computational and storage limitations.

Discusses advantages and limitations of the proposed design.

Abstract

The synergy between Federated Learning and blockchain has been considered promising; however, the computationally intensive nature of contribution measurement conflicts with the strict computation and storage limits of blockchain systems. We propose a novel concept to decentralize the AI training process using blockchain technology and Multi-task Peer Prediction. By leveraging smart contracts and cryptocurrencies to incentivize contributions to the training process, we aim to harness the mutual benefits of AI and blockchain. We discuss the advantages and limitations of our design.