FeAdaBoost: Enhancing Federated Learning Accuracy by Ensemble Techniques

Federated Learning (FL), an advanced technique in machine learning (ML), allows for model training without transferring data to a central server. This method is particularly valuable in sensitive applications, such as healthcare and finance, as it preserves data privacy and reduces security risks. However, FL faces the challenge of reduced accuracy compared to centralized approaches due to limited access to the full dataset. To address this issue, we propose a solution that integrates the ensemble learning method AdaBoost with FL, which we call FeAdaBoost. We validate the effectiveness of our approach using the task of classifying a chest X-ray image dataset. The experimental results confirm that the proposed approach significantly improves both accuracy and efficiency compared to traditional FL.