Federated Learning Drift Detection: An Empirical Study on the Impact of Concept and Data Drift
Leyla Rahimli, Feras M. Awaysheh, Sawsan Al Zubi, Sadi Alawadi
Abstract
Federated Learning (FL) has emerged as a transformative paradigm in machine learning, enabling decentralized model training while preserving data privacy across multiple clients. FL addresses critical privacy concerns but introduces challenges related to model drift. Model drift is a phenomenon where the model degrades over time due to changes in the underlying data distribution or the relationships between input features and target variables. This paper proposes a novel drift detection and management methodology within federated environments. Our experimental analysis demonstrates the effectiveness of the proposed drift detection framework. The study systematically evaluates the impact of drift on model performance metrics, including accuracy, F1 score, Cohen's kappa, and ROC. The findings indicate that even minimal drift in a subset of clients can significantly degrade the global model's performance, underscoring the importance of robust drift detection. The proposed solution enhances the reliability and accuracy of federated models and addresses the scalability and privacy-preserving requirements inherent in FL environments.