FedDAP：域偏移下联邦学习的域感知原型学习
FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift
在联邦场景下按域聚合类原型、并做同域拉近/异域推远的双对齐，可作为视觉模型跨域泛化时构造域感知类中心、替代单一全局原型的可复用手段。
原文依据 construct domain-specific global prototypes by aggregating local client prototypes within the same domain using a similarity-weighted fusion mechanism
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）使多个客户端能够在不暴露私有数据的情况下进行去中心化模型训练，因而适用于隐私敏感的应用。然而，在真实的联邦学习场景中，客户端往往持有来自不同域的数据，导致严重的域偏移并使全局模型性能下降。为此，原型学习作为一种有前景的解决方案出现，它利用类别级的特征表示。然而，现有方法存在两个关键局限：（1）现有的基于原型的联邦学习方法通常通过聚合所有客户端的局部原型来为每个类别构建单一全局原型，而不保留域信息。（2）当前的特征-原型对齐是域无关的，迫使客户端无论域来源如何都对齐到全局原型。为应对这些挑战，我们提出联邦域感知原型（FedDAP），通过相似度加权融合机制在同一域内聚合局部客户端原型，从而构建域特定的全局原型。这些全局域特定原型随后被用于指导局部训练：将局部特征与同一域的原型对齐，同时鼓励其与不同域的原型分离。这种双重对齐增强了局部层面的域特定学习，并使全局模型能够泛化到多样的域。最后，我们在三个不同数据集 DomainNet、Office-10 和 PACS 上进行了大量实验，以证明所提框架在应对域偏移挑战方面的有效性。
英文原文摘要 1609 字符
Federated Learning (FL) enables decentralized model training across multiple clients without exposing private data, making it ideal for privacy-sensitive applications. However, in real-world FL scenarios, clients often hold data from distinct domains, leading to severe domain shift and degraded global model performance. To address this, prototype learning has been emerged as a promising solution, which leverages class-wise feature representations. Yet, existing methods face two key limitations: (1) Existing prototype-based FL methods typically construct a single global prototype per class by aggregating local prototypes from all clients without preserving domain information. (2) Current feature-prototype alignment is domain-agnostic, forcing clients to align with global prototypes regardless of domain origin. To address these challenges, we propose Federated Domain-Aware Prototypes (FedDAP) to construct domain-specific global prototypes by aggregating local client prototypes within the same domain using a similarity-weighted fusion mechanism. These global domain-specific prototypes are then used to guide local training by aligning local features with prototypes from the same domain, while encouraging separation from prototypes of different domains. This dual alignment enhances domain-specific learning at the local level and enables the global model to generalize across diverse domains. Finally, we conduct extensive experiments on three different datasets: DomainNet, Office-10, and PACS to demonstrate the effectiveness of our proposed framework to address the domain shift challenges.