A Blockchain-Empowered Multiaggregator Federated Learning Architecture in Edge Computing With Deep Reinforcement Learning Optimization

Federated learning (FL) is emerging as a sought-after distributed machine learning architecture, offering the advantage of model training without direct exposure to raw data. With advancements in network infrastructure, FL has been seamlessly integrated into edge computing. However, the limited resources on edge devices introduce security vulnerabilities to FL in the context. While blockchain technology promises to bolster security, practical deployment on resource-constrained edge devices remains a challenge. Moreover, the exploration of FL with multiple aggregators in edge computing is still new in the literature. Addressing these gaps, we introduce the blockchain-empowered heterogeneous multiaggregator federated learning architecture (BMA-FL). We design a novel lightweight Byzantine consensus mechanism, namely PBCM, to enable secure and fast model aggregation and synchronization in BMA-FL. We study the heterogeneity problem in BMA-FL that the aggregators are associated with varied number of connected trainers with non-IID data distributions and diverse training speed. We propose a multiagent deep reinforcement learning algorithm (MASB-DRL) to help aggregators decide the best training strategies. Experiments on real-word datasets demonstrate the efficiency of BMA-FL to achieve better models faster than baselines, showing the efficacy of PBCM and MASB-DRL.