FedADP: Unified Model Aggregation for Federated Learning with Heterogeneous Model Architectures

TL;DR

FedADP is a federated learning framework that dynamically adapts to diverse client model architectures, significantly improving accuracy and efficiency in heterogeneous environments.

Contribution

It introduces a novel aggregation method that accommodates different model architectures, enhancing collaboration and performance in federated learning with heterogeneous clients.

Findings

Achieves up to 23.30% accuracy improvement over existing methods.

Effectively handles client heterogeneity in model architectures.

Enhances resource utilization and training efficiency.

Abstract

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.