arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.01334cs.LGcs.AI
收藏

联邦域泛化:综述

Federated Domain Generalization: A Survey

College of Computer Science and Engineering, Northeastern University(计算机科学与工程学院,东北大学);Distributed Systems Group, TU Wien(分布式系统组,TU Wien);College of Software, Northeastern University(软件学院,东北大学);College of Information Science and Engineering, Northeastern University(信息科学与工程学院,东北大学)

Ying Li, Xingwei Wang, Rongfei Zeng, Praveen Kumar Donta, Ilir Murturi, Min Huang, Schahram Dustdar

AI总结:

本文首次系统综述联邦域泛化(FDG),梳理其从传统机器学习到域适应与域泛化的发展脉络,将现有方法分为联邦域对齐、数据操作、学习策略和聚合优化四类,并总结常用数据集、评估基准及未来研究方向。

摘要:

机器学习通常依赖于训练分布与测试分布相同且数据集中存储用于训练和测试的假设。然而,在现实场景中,分布可能差异显著,数据往往分布在不同的设备、组织或边缘节点上。因此,开发能够有效泛化到未见分布且数据跨不同域分布的模型势在必行。为应对这一挑战,近年来人们对联邦域泛化(FDG)的兴趣激增。FDG 结合了联邦学习(FL)和域泛化(DG)技术的优势,使多个源域能够在保护数据隐私的同时,协同学习一个能够直接泛化到未见域的模型。然而,在域偏移下泛化联邦模型是一个技术上具有挑战性的问题,迄今为止在研究领域受到的关注很少。本文首次对该领域的最新进展进行了综述。首先,我们讨论了从传统机器学习到域适应和域泛化,再到 FDG 的发展过程,并给出了相应的形式化定义。然后,我们将近年来的方法分为四类:联邦域对齐、数据操作、学习策略和聚合优化,并详细介绍了每一类中的合适算法。接下来,我们介绍了常用的数据集、应用、评估和基准。最后,我们通过提供一些未来潜在的研究主题来总结本综述。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑