Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges

TL;DR

This paper provides a comprehensive overview of decentralized federated learning, analyzing its fundamentals, frameworks, applications, and challenges, highlighting differences from centralized approaches and exploring future trends.

Contribution

It offers the first detailed comparison of DFL and CFL, reviews existing frameworks, and identifies key challenges and future directions in DFL research.

Findings

DFL reduces reliance on central servers and improves robustness.

Comparison of DFL frameworks reveals diverse architectures and communication strategies.

Identification of open challenges guides future research in DFL.

Abstract

In recent years, Federated Learning (FL) has gained relevance in training collaborative models without sharing sensitive data. Since its birth, Centralized FL (CFL) has been the most common approach in the literature, where a central entity creates a global model. However, a centralized approach leads to increased latency due to bottlenecks, heightened vulnerability to system failures, and trustworthiness concerns affecting the entity responsible for the global model creation. Decentralized Federated Learning (DFL) emerged to address these concerns by promoting decentralized model aggregation and minimizing reliance on centralized architectures. However, despite the work done in DFL, the literature has not (i) studied the main aspects differentiating DFL and CFL; (ii) analyzed DFL frameworks to create and evaluate new solutions; and (iii) reviewed application scenarios using DFL. Thus, this article identifies and analyzes the main fundamentals of DFL in terms of federation architectures, topologies, communication mechanisms, security approaches, and key performance indicators. Additionally, the paper at hand explores existing mechanisms to optimize critical DFL fundamentals. Then, the most relevant features of the current DFL frameworks are reviewed and compared. After that, it analyzes the most used DFL application scenarios, identifying solutions based on the fundamentals and frameworks previously defined. Finally, the evolution of existing DFL solutions is studied to provide a list of trends, lessons learned, and open challenges.