[论文解读] Federated Domain Generalization: A Survey

Ying Li, Xingwei Wang+5 more|arXiv (Cornell University)|Jun 2, 2023

Domain Adaptation and Few-Shot Learning被引用 26

一句话总结

这是第一份关于 Federated Domain Generalization (FDG) 的全面综述，概述理论、方法、数据集、应用、评估、基准以及未来方向。

ABSTRACT

Machine learning typically relies on the assumption that training and testing distributions are identical and that data is centrally stored for training and testing. However, in real-world scenarios, distributions may differ significantly and data is often distributed across different devices, organizations, or edge nodes. Consequently, it is imperative to develop models that can effectively generalize to unseen distributions where data is distributed across different domains. In response to this challenge, there has been a surge of interest in federated domain generalization (FDG) in recent years. FDG combines the strengths of federated learning (FL) and domain generalization (DG) techniques to enable multiple source domains to collaboratively learn a model capable of directly generalizing to unseen domains while preserving data privacy. However, generalizing the federated model under domain shifts is a technically challenging problem that has received scant attention in the research area so far. This paper presents the first survey of recent advances in this area. Initially, we discuss the development process from traditional machine learning to domain adaptation and domain generalization, leading to FDG as well as provide the corresponding formal definition. Then, we categorize recent methodologies into four classes: federated domain alignment, data manipulation, learning strategies, and aggregation optimization, and present suitable algorithms in detail for each category. Next, we introduce commonly used datasets, applications, evaluations, and benchmarks. Finally, we conclude this survey by providing some potential research topics for the future.

研究动机与目标

• 介绍从传统机器学习到领域自适应和领域泛化的发展轨迹，进而引出 FDG 及其形式定义。
• 将 FDG 方法学分为四类：federated domain alignment、data manipulation、learning strategies、aggregation optimization，并对每一类给出详细算法。
• 介绍在 FDG 中常用的数据集、应用、评估和基准。
• 讨论未来研究方向和可能的议题以推动 FDG 工作。

提出的方法

• 将 FDG 方法分类为四类：federated domain alignment、data manipulation、learning strategies、aggregation optimization。
• 对每一类给出适用算法的详细介绍。
• 对 FDG 概念及相关界限的形式定义与理论讨论。
• 给出统一的 FDG 架构/工作流示意，以指导未来研究和应用。
• 讨论数据集、应用、评估和基准，以规范 FDG 研究。

实验结果

研究问题

• RQ1 在 FDG 设置中，Federated Domain Generalization 如何被定义和形式化？
• RQ2 FDG 的主要方法学类别有哪些？有哪些算法是其典型代表？
• RQ3 FDG 存在哪些数据集、应用、评估和基准，它们如何指导未来工作？
• RQ4 为推进 FDG 建议的未来研究方向是什么？

主要发现

• FDG 被定位为联邦学习与领域泛化的整合，以在保护数据隐私的同时实现对未见领域的泛化。
• FDG 方法学分为四类：federated domain alignment、data manipulation、learning strategies、aggregation optimization。
• 该综述提供了与 FDG 相关的数据集、应用、评估和基准的有序汇编。
• 作者讨论了推动 FDG 领域发展的潜在未来研究主题和方向，突出未解决的挑战与机遇。