A hierarchical blockchain architecture for federated learning in edge computing networks

Abstract

Blockchain-based federated learning (FL) has recently garnered significant attention as a trusted decentralized learning paradigm. However, traditional FL faces critical challenges: synchronous FL suffers from stragglers that delay training, while asynchronous FL risks model instability due to inconsistent updates. Moreover, processing blockchain consensus protocols incurs substantial resource consumption and operational latency. To overcome these challenges, we propose a hierarchical blockchain architecture for semi-asynchronous FL that balances efficiency and security. Our approach features a two-layer design: (1) a training layer, where edge nodes asynchronously upload local models via a directed acyclic graph (DAG) to mitigate stragglers and ensure continuous progress, and (2) a blockchain layer, which periodically validates and synchronously aggregates models to maintain stability and defend against malicious inputs. We further introduce novel DAG-based transaction tracking and uploading algorithms to enhance efficiency, enabling rapid local updates while ensuring global model integrity through blockchain consensus. Experimental results demonstrate that our system reduces latency by 26% compared to typical blockchain-based FL approaches, while maintaining a stable convergence rate and high training accuracy. By harmonizing asynchronous flexibility with synchronous control, our work enhances the scalability and robustness of FL in resource-constrained edge environments.