FLOW: A Scalable Multi-Model Federated Learning Framework on the Wheels

The highly mobility nature of connected vehicles poses significant challenges in the research area of federated learning, and to the best of our knowledge, the existing federated learning approaches do not consider the problem of training multi-model for constantly on-the-wheel moving vehicles. To bridge this gap, we design and implement FLOW, a scalable multi-model federated learning framework for highly mobile connected vehicles, which includes three essential components: (1) a dynamic client vehicle selection algorithm to deal with problems such as signal loss or weak signals, which may prevent some vehicles from participating in the training cluster; (2) a well-designed model allocation algorithm to select appropriate vehicle computing units for specific model training tasks; (3) geofencing not independent and identically distributed (non-i.i.d) data training, which can make models more robust and generalizable to different geographic driving area. Finally, we compare the proposed framework with centralized training and explore the performance of four aggregation protocols. The experiment results demonstrated the effectiveness of FLOW for the real-world applications.