Principles and Components of Federated Learning Architectures

TL;DR

This paper explains the core principles and architectural components of federated learning, addressing key challenges and proposing patterns based on a systematic literature survey to enhance understanding and future development.

Contribution

It provides a comprehensive overview of federated learning architecture, including key domains, limitations, and architectural patterns derived from systematic literature review.

Findings

Identifies key domains: system heterogeneity, data partitioning, models, communication, privacy.

Highlights limitations and challenges in federated learning.

Proposes architectural patterns for federated learning systems.

Abstract

Federated Learning (FL) is a machine learning framework where multiple clients, from mobiles to enterprises, collaboratively construct a model under the orchestration of a central server but still retain the decentralized nature of the training data. This decentralized training of models offers numerous advantages, including cost savings, enhanced privacy, improved security, and compliance with legal requirements. However, for all its apparent advantages, FL is not immune to the limitations of conventional machine learning methodologies. This article provides an elaborate explanation of the inherent concepts and features found within federated learning architecture, addressing five key domains: system heterogeneity, data partitioning, machine learning models, communication protocols, and privacy techniques. This article also highlights the limitations in this domain and proposes avenues for future work. Besides, we provide a set of architectural patterns for federated learning systems, which are derived from the systematic survey of the literature. The main elements of FL, the fundamentals of Federated Learning, and a few architectural specifics will all be better understood with the aid of this research.