Centralized vs Decentralized Federated Learning: A trade-off performance analysis
It provides a practical comparison of FL architectures for practitioners choosing between centralized and decentralized approaches, though the analysis is limited to a single dataset and model.
This paper experimentally compares centralized, decentralized, and semi-decentralized federated learning architectures using the Fedstellar simulator, MNIST dataset, and MLP classifier, revealing trade-offs in performance indicators such as accuracy, convergence time, and communication overhead.
Federated Learning (FL) has emerged as a promising paradigm for collaborative model training across distributed edge devices while preserving data privacy especially with the huge increase amount of data due to the adoption of technologies which contributes to the growing number of IoT devices. Storing this amount of data centrally is challenging due to issues like limited communication, privacy, and regulations. FL can be Centralized (CFL), Decentralized (DFL), and Semi-decentralized (SDFL). Choosing the right FL architecture depends on the application's needs. However, very few research studies have experimentally compared these three types of architectures to not only understand the respective strengths and limitations, but also trade-offs between different performance indicators. This paper overcome this lack of analysis, conducting experimental analyses using the Fedstellar simulator, MNIST dataset, and MLP classifier.