Trustless Federated Learning at Edge-Scale: A Compositional Architecture for Decentralized, Verifiable, and Incentive-Aligned Coordination
This work addresses the problem of enabling trustless and scalable federated learning for edge devices, representing a novel method rather than an incremental improvement.
The paper tackled the problem of realizing decentralized, verifiable, and incentive-aligned federated learning at edge-scale by addressing gaps in accountability, economic mechanisms, scalability, and governance, resulting in a compositional architecture that uses cryptographic receipts, geometric novelty measurement, parallel object ownership, and time-locked policies.
Artificial intelligence is retracing the Internet's path from centralized provision to distributed creation. Initially, resource-intensive computation concentrates within institutions capable of training and serving large models.Eventually, as federated learning matures, billions of edge devices holding sensitive data will be able to collectively improve models without surrendering raw information, enabling both contribution and consumption at scale. This democratic vision remains unrealized due to certain compositional gaps; aggregators handle updates without accountability, economic mechanisms are lacking and even when present remain vulnerable to gaming, coordination serializes state modifications limiting scalability, and governance permits retroactive manipulation. This work addresses these gaps by leveraging cryptographic receipts to prove aggregation correctness, geometric novelty measurement to prevent incentive gaming, parallel object ownership to achieve linear scalability, and time-locked policies to check retroactive manipulation.