[论文解读] Recent Advances on Federated Learning: A Systematic Survey

Bingyan Liu, Nuoyan Lv+2 more|arXiv (Cornell University)|Jan 3, 2023

Privacy-Preserving Technologies in Data被引用 8

一句话总结

系统性综述联邦学习，提出四维度分类法，评述聚合、异质性、安全与公平性的方法、框架及未来方向。

ABSTRACT

Federated learning has emerged as an effective paradigm to achieve privacy-preserving collaborative learning among different parties. Compared to traditional centralized learning that requires collecting data from each party, in federated learning, only the locally trained models or computed gradients are exchanged, without exposing any data information. As a result, it is able to protect privacy to some extent. In recent years, federated learning has become more and more prevalent and there have been many surveys for summarizing related methods in this hot research topic. However, most of them focus on a specific perspective or lack the latest research progress. In this paper, we provide a systematic survey on federated learning, aiming to review the recent advanced federated methods and applications from different aspects. Specifically, this paper includes four major contributions. First, we present a new taxonomy of federated learning in terms of the pipeline and challenges in federated scenarios. Second, we summarize federated learning methods into several categories and briefly introduce the state-of-the-art methods under these categories. Third, we overview some prevalent federated learning frameworks and introduce their features. Finally, some potential deficiencies of current methods and several future directions are discussed.

研究动机与目标

• 基于流水线与挑战（聚合、异质性、隐私、公平性）提出一个新的联邦学习分类法。
• 在每个分类中总结最先进的FL方法。
• 概述现有的主流FL框架及其特征。
• 讨论当前存在的不足并提出FL研究的未来方向。

提出的方法

• 提出一个将FL方法与主线流程与挑战对齐的分类法。
• 将FL方法分为聚合优化、异质性FL、安全FL和公平FL。
• 简要描述各类别下具有代表性的方法（如 FedAvg、FedMA、FedProx）。
• 综述FL框架及其部署层面。
• 讨论FL的局限性及未来研究方向。

实验结果

研究问题

• RQ1 基于FL管道和挑战，什么是有效的联邦学习分类法？
• RQ2 聚合优化、异质性FL、安全FL和公平FL领域的前沿方法有哪些？
• RQ3 存在哪些FL框架，它们为实际部署提供了哪些特性？
• RQ4 当前FL方法存在哪些不足，未来方向最具潜力？

主要发现

• 提出四类分类法：聚合优化、异质性联邦学习、安全联邦学习、以及公平联邦学习。
• 在分类法下回顾具有代表性的方法和框架，反映最新进展。
• 强调隐私、安全威胁及公平性问题是FL研究的核心挑战。
• 讨论潜在的不足并勾勒推进FL理论与实践的未来方向。
• 指出自2020年以来FL研究的上升趋势，以及对及时、全面综述的需求。