Decentralized Collaborative Learning with Probabilistic Data Protection

TL;DR

This paper proposes a decentralized federated multi-task learning framework that leverages blockchain technology and expander graph topologies to enhance privacy, scalability, and collaborative insights in distributed machine learning.

Contribution

It introduces a novel combination of blockchain-based consensus algorithms with federated multi-task learning to improve privacy and scalability in decentralized settings.

Findings

Expander graph topology significantly improves consensus scalability.

The framework preserves privacy while enabling collaborative learning.

Open problems in decentralized machine learning are discussed.

Abstract

We discuss future directions of Blockchain as a collaborative value co-creation platform, in which network participants can gain extra insights that cannot be accessed when disconnected from the others. As such, we propose a decentralized machine learning framework that is carefully designed to respect the values of democracy, diversity, and privacy. Specifically, we propose a federated multi-task learning framework that integrates a privacy-preserving dynamic consensus algorithm. We show that a specific network topology called the expander graph dramatically improves the scalability of global consensus building. We conclude the paper by making some remarks on open problems.