On-Device Federated Learning via Blockchain and its Latency Analysis
share
In this letter, we propose a block-chained federated learning (BlockFL) architecture, where mobile devices' local learning model updates are exchanged and verified by leveraging blockchain. This enables on-device machine learning without any central coordination, even when each device lacks its own training data samples. We investigate the end-to-end learning completion latency of BlockFL, thereby yielding the optimal block generation rate as well as important insights in terms of network scalability and robustness.
READ FULL TEXT