Decentralized consensus and governance for collaborative intelligence

• Main Author: LIU, Huiwen
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Decentralization; Collaborative Intelligence; Consensus; Governance; Artificial Intelligence and Robotics; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/etd_coll/633; https://ink.library.smu.edu.sg/context/etd_coll/article/1632/viewcontent/GPIS_AY2018_PhD_Huiwen_Liu.pdf
• Institution: Singapore Management University

The data economy today is becoming increasingly collaborative in nature. Take business intelligence, for example. To unleash the full potential of big data, it is essential to integrate multi-source data depicting entities from a multi-faceted and multi-modal perspective, which, not surprisingly, is not achievable by any company alone. In collaborative intelligence, there are two core issues, namely "trust" and "incentive". The core mechanisms to solve these two problems are consensus and tokenization separately. To solve the trust problem more effectively, we propose a systematic consensus evaluation framework to investigate whether existing consensus algorithms can do so. After a lot of research and evaluation, 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. So, 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 of learning efficiency and system liveliness from asynchronous societal-scale PoW-style learning but also the finality of consensus and reward allocation from epoch-based BFT-style voting. To mitigate false reward claims by data forgery from Byzantine attacks, a privacy-aware data verification and contribution-based reward allocation mechanism is designed to complete the framework. To solve the incentive problem, we investigated the mainstream DAO governance system from the tokenization governance perspective and proposed a four-layer governance evaluation framework. Through the core decentralized analysis, we aimed to illustrate the challenges of building a truly decentralized governance system and prepare for the design of a relatively perfect tokenization governance system.