Multi-Criteria Clustering and Client Selection for Heterogeneous Federated Learning
Maryam Ben Driss, Essaïd Sabir, Halima Elbiaze · 2025
Federated learning (FL) faces significant challenges due to the non-independent and identically distributed (non-IID) data and the heterogeneous nature of clients’ characteristics. Clustered federated learning (CFL) addresses these issues by grouping similar clients and creating cluster-specific models. However, CFL introduces additional challenges, such as determining the optimal clustering criteria and managing the dynamic nature of client availability and data distribution. This paper proposes a novel CFL approach that integrates a full spectrum of relevant factors where clients are clustered based on data distribution, device type, and geographical location. Each group selects a subset of clients based on the information’s age, the client’s motivation, and the availability of resources to participate in the learning process. Unlike previous approaches that focus on a limited set of criteria, our method considers a holistic view of client attributes to improve clustering performance. The experimental results demonstrate the efficiency and effectiveness of the proposed method, highlighting significant improvements in communication efficiency and model quality. Furthermore, our approach adapts dynamically to changes in client availability, ensuring robust learning over time. By optimizing client selection and leveraging cluster-specific characteristics, the proposed approach enhances the scalability, robustness, and overall performance of FL systems.