FedADP: Unified Model Aggregation for Federated Learning with Heterogeneous Model Architectures
This addresses efficiency and accuracy challenges in federated learning for real-world heterogeneous settings, representing a strong specific gain rather than a foundational advancement.
The paper tackled the problem of federated learning in heterogeneous environments with diverse client model architectures, proposing FedADP to dynamically adjust architectures during aggregation, which improved accuracy by up to 23.30% compared to existing methods.
Traditional Federated Learning (FL) faces significant challenges in terms of efficiency and accuracy, particularly in heterogeneous environments where clients employ diverse model architectures and have varying computational resources. Such heterogeneity complicates the aggregation process, leading to performance bottlenecks and reduced model generalizability. To address these issues, we propose FedADP, a federated learning framework designed to adapt to client heterogeneity by dynamically adjusting model architectures during aggregation. FedADP enables effective collaboration among clients with differing capabilities, maximizing resource utilization and ensuring model quality. Our experimental results demonstrate that FedADP significantly outperforms existing methods, such as FlexiFed, achieving an accuracy improvement of up to 23.30%, thereby enhancing model adaptability and training efficiency in heterogeneous real-world settings.