Centralized vs Decentralized Federated Learning: A trade-off performance analysis

TL;DR

This paper compares centralized, decentralized, and semi-decentralized federated learning architectures through experimental analysis to understand their performance trade-offs.

Contribution

It provides the first comprehensive experimental comparison of different FL architectures using Fedstellar, MNIST, and MLP.

Findings

Decentralized FL offers better privacy but higher communication costs.

Centralized FL achieves higher accuracy with lower latency.

Semi-decentralized FL balances privacy and performance.

Abstract

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.