将联邦学习拆解为可组合模块，帮研究者系统理解其核心机制。
Modular Federated Learning: A Meta-Framework Perspective
- 把联邦学习看作通信、优化、安全等模块的组合，结构化分析。
- 提出新分类：聚合与对齐并列，对齐是关键操作之一。
- 梳理主流框架和未解问题，适合想深入或落地的开发者。
联邦学习（FL）在保护隐私的前提下实现分布式机器学习训练，是数据敏感与去中心化场景下的范式革新。尽管发展迅速，FL仍复杂多面，需系统性理解其方法、挑战与应用。本文从元框架视角出发，将FL视为通信、优化、安全与隐私等模块的组合，系统解析其核心环节。追溯了从分布式优化到现代分布式学习的发展脉络。提出新颖分类：区分聚合与对齐，并将对齐作为与聚合并列的基本操作。为连接理论与实践，分析了现有的Python FL框架，支持实际部署。最后，系统归纳各子领域的关键挑战，揭示元框架内各模块的开放研究问题。通过模块化结构与聚合-对齐双核心视角，本综述为理解与推进FL研究与应用提供全面且可扩展的基础。
原文摘要 · Abstract (English)
Federated Learning (FL) enables distributed machine learning training while preserving privacy, representing a paradigm shift for data-sensitive and decentralized environments. Despite its rapid advancements, FL remains a complex and multifaceted field, requiring a structured understanding of its methodologies, challenges, and applications. In this survey, we introduce a meta-framework perspective, conceptualising FL as a composition of modular components that systematically address core aspects such as communication, optimisation, security, and privacy. We provide a historical contextualisation of FL, tracing its evolution from distributed optimisation to modern distributed learning paradigms. Additionally, we propose a novel taxonomy distinguishing Aggregation from Alignment, introducing the concept of alignment as a fundamental operator alongside aggregation. To bridge theory with practice, we explore available FL frameworks in Python, facilitating real-world implementation. Finally, we systematise key challenges across FL sub-fields, providing insights into open research questions throughout the meta-framework modules. By structuring FL within a meta-framework of modular components and emphasising the dual role of Aggregation and Alignment, this survey provides a holistic and adaptable foundation for understanding and advancing FL research and deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。