Decentralized Collaborative Learning with Probabilistic Data Protection
This work addresses the problem of enabling secure and scalable decentralized machine learning for network participants seeking collaborative insights, though it appears incremental as it builds on existing federated learning concepts.
The paper tackles the challenge of decentralized collaborative learning by proposing a federated multi-task learning framework with a privacy-preserving dynamic consensus algorithm, showing that using an expander graph topology improves scalability in global consensus building.
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.