Proof-of-Data: A Consensus Protocol for Collaborative Intelligence
Huiwen Liu, Feida Zhu, Ling Cheng

TL;DR
This paper introduces Proof-of-Data, a blockchain-based decentralized federated learning protocol that ensures Byzantine fault tolerance, fair reward distribution, and maintains high model training performance without a central authority.
Contribution
It proposes a novel PoD consensus protocol that decouples model training from contribution accounting, enabling efficient, fair, and decentralized federated learning with Byzantine fault tolerance.
Findings
Model training performance close to centralized systems
Achieves Byzantine fault tolerance with 1/3 ratio
Ensures fair reward allocation and trust in consensus
Abstract
Existing research on federated learning has been focused on the setting where learning is coordinated by a centralized entity. Yet the greatest potential of future collaborative intelligence would be unleashed in a more open and democratized setting with no central entity in a dominant role, referred to as "decentralized federated learning". New challenges arise accordingly in achieving both correct model training and fair reward allocation with collective effort among all participating nodes, especially with the threat of the Byzantine node jeopardising both tasks. In this paper, we propose a blockchain-based decentralized Byzantine fault-tolerant federated learning framework based on a novel Proof-of-Data (PoD) consensus protocol to resolve both the "trust" and "incentive" components. By decoupling model training and contribution accounting, PoD is able to enjoy not only the benefit…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSemantic Web and Ontologies · Logic, Reasoning, and Knowledge
