Architecture and Aggregation Strategies of Federated Broad Learning System: a Feasibility Study

This study investigates the feasibility of incorporating the broad learning (BL) model in federated learning. Traditional deep learning-based federated learning encounters challenges such as excessive communication volume and extended training time. To address these issues, federated learning with the broad learning model has attracted much attention. We provide a detailed discussion on server-side aggregation for BL models, including the initialization process and three feasible aggregation approaches for single-round aggregation. Then, ablation studies are conducted to assess the suitable BL model architectures within the context of federated learning. Furthermore, we perform a comparative analysis between these approaches and existing federated learning schemes to evaluate their advantages and limitations. Our research suggests that federated learning with BL models is highly feasible in certain scenarios and can effectively tackle the issues of transmission efficiency. Finally, we analyze our findings and propose further investigation to improve algorithms for more efficient performance of federated broad learning systems in the future.