HFedATM：基于最优传输与正则化均值聚合的分层联邦域泛化
HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation
Filter-wise 最优传输对齐 + 收缩正则均值聚合，可作为跨客户端/跨站点模型参数融合的通用手段，用于视觉模型在非独立同分布数据上的域泛化；其分层聚合思路可迁移到多源视觉数据（如多医院影像、多摄像头场景）的分布式训练。
原文依据 aligns the convolutional filters of models from different stations through Filter-wise Optimal Transport Alignment
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论联邦学习（FL）是一种去中心化方法，多个客户端在不共享原始数据的前提下协作训练一个共享的全局模型。尽管其有效，但随着参与设备数量增长，传统 FL 因对单一中心服务器提出过高的计算与通信需求而面临可扩展性挑战。分层联邦学习（HFL）通过将模型聚合任务分散到中间节点（站点）来解决这些问题，从而提升系统可扩展性与对单点故障的鲁棒性。然而，HFL 仍受制于一个关键却常被忽视的局限：域偏移，即不同客户端与站点之间的数据分布差异显著，导致模型在未见目标域上的性能下降。尽管已有联邦域泛化（FedDG）方法被提出以提升对域偏移的鲁棒性，但将其集成进 HFL 框架的研究仍基本空白。本文正式提出分层联邦域泛化（HFedDG），这是一个用于研究分层架构中域偏移的新场景。具体而言，我们提出 HFedATM，一种分层聚合方法：首先通过滤波器级最优传输对齐（Filter-wise Optimal Transport Alignment）对齐来自不同站点的模型卷积滤波器，随后使用收缩感知的正则化均值聚合（Shrinkage-aware Regularized Mean Aggregation）合并对齐后的模型。大量实验评估表明，HFedATM 在多个数据集上显著提升现有 FedDG 基线的性能，并保持计算与通信效率。此外，理论分析表明，与标准分层平均相比，HFedATM 取得更紧的泛化误差界，从而带来更快的收敛与稳定的训练行为。
英文原文摘要 1868 字符
Federated Learning (FL) is a decentralized approach where multiple clients collaboratively train a shared global model without sharing their raw data. Despite its effectiveness, conventional FL faces scalability challenges due to excessive computational and communication demands placed on a single central server as the number of participating devices grows. Hierarchical Federated Learning (HFL) addresses these issues by distributing model aggregation tasks across intermediate nodes (stations), thereby enhancing system scalability and robustness against single points of failure. However, HFL still suffers from a critical yet often overlooked limitation: domain shift, where data distributions vary significantly across different clients and stations, reducing model performance on unseen target domains. While Federated Domain Generalization (FedDG) methods have emerged to improve robustness to domain shifts, their integration into HFL frameworks remains largely unexplored. In this paper, we formally introduce Hierarchical Federated Domain Generalization (HFedDG), a novel scenario designed to investigate domain shift within hierarchical architectures. Specifically, we propose HFedATM, a hierarchical aggregation method that first aligns the convolutional filters of models from different stations through Filter-wise Optimal Transport Alignment and subsequently merges aligned models using a Shrinkage-aware Regularized Mean Aggregation. Our extensive experimental evaluations demonstrate that HFedATM significantly boosts the performance of existing FedDG baselines across multiple datasets and maintains computational and communication efficiency. Moreover, theoretical analyses indicate that HFedATM achieves tighter generalization error bounds compared to standard hierarchical averaging, resulting in faster convergence and stable training behavior.