Decentralized Intelligence Network (DIN)
It addresses data access and sovereignty issues for AI developers and data owners, but it is incremental as it builds on existing federated learning and blockchain concepts.
The paper tackles data fragmentation and siloing in AI development by proposing the Decentralized Intelligence Network (DIN), a theoretical framework that uses personal data stores, federated learning on a blockchain, and a cryptographic rewards mechanism to enable decentralized AI training while keeping data under participants' control.
Decentralized Intelligence Network (DIN) is a theoretical framework designed to address challenges in AI development, particularly focusing on data fragmentation and siloing issues. It facilitates effective AI training within sovereign data networks by overcoming barriers to accessing diverse data sources, leveraging: 1) personal data stores to ensure data sovereignty, where data remains securely within Participants' control; 2) a scalable federated learning protocol implemented on a public blockchain for decentralized AI training, where only model parameter updates are shared, keeping data within the personal data stores; and 3) a scalable, trustless cryptographic rewards mechanism on a public blockchain to incentivize participation and ensure fair reward distribution through a decentralized auditing protocol. This approach guarantees that no entity can prevent or control access to training data or influence financial benefits, as coordination and reward distribution are managed on the public blockchain with an immutable record. The framework supports effective AI training by allowing Participants to maintain control over their data, benefit financially, and contribute to a decentralized, scalable ecosystem that leverages collective AI to develop beneficial algorithms.