Hierarchical Federated Learning for Edge Intelligence through Average Consensus

Consensus of multi-agent systems has recently been studied in the context of Federated Learning (FL), an emerging branch of distributed machine learning. The present paper proposes a two-level hierarchical algorithm for FL in the context of edge computing, developing a fully decentralized solution that relies on results obtained for discrete-time consensus of dynamical systems. The proposed architecture and algorithm are validated on a test case and compared to current solutions, which require a centralized server.