解决单源联邦学习中跨域泛化差的问题
FedGCA: Global Consistent Augmentation Based Single-Source Federated Domain Generalization
- 用风格补全模块生成多样域风格数据
- 通过全局语义与类别一致性约束提升泛化能力
- 适合缺乏多域数据的联邦学习场景
联邦域泛化（FedDG）旨在利用多域训练样本训练出能在未见域上表现良好的全局模型。然而，联邦学习网络中的客户端通常受限于单一非独立同分布（non-IID）域，受采样和时间限制影响。缺乏跨域交互及域内差异导致难以学习共性特征，限制了现有方法的性能，即单源联邦域泛化（sFedDG）问题。为此，我们提出联邦全局一致增强（FedGCA）方法，引入风格补全模块，对数据样本进行多样化域风格增强。为确保增强样本有效融合，FedGCA同时采用全局引导的语义一致性和类别一致性，缓解单个客户端内部局部语义不一致以及多个客户端间类别不一致问题。大量实验验证了该方法的优越性。
原文摘要 · Abstract (English)
Federated Domain Generalization (FedDG) aims to train the global model for generalization ability to unseen domains with multi-domain training samples. However, clients in federated learning networks are often confined to a single, non-IID domain due to inherent sampling and temporal limitations. The lack of cross-domain interaction and the in-domain divergence impede the learning of domain-common features and limit the effectiveness of existing FedDG, referred to as the single-source FedDG (sFedDG) problem. To address this, we introduce the Federated Global Consistent Augmentation (FedGCA) method, which incorporates a style-complement module to augment data samples with diverse domain styles. To ensure the effective integration of augmented samples, FedGCA employs both global guided semantic consistency and class consistency, mitigating inconsistencies from local semantics within individual clients and classes across multiple clients. The conducted extensive experiments demonstrate the superiority of FedGCA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。