FedSA：通过语义锚点实现统一表示学习的基于原型的联邦学习
FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning
AI总结：
针对联邦学习中统计与模型异构导致的原型不一致问题，提出 FedSA 用语义锚点解耦原型生成，并结合对比正则化与分类器校准学习统一表示。
摘要：
基于原型的联邦学习已成为一种很有前景的方法，它通过共享轻量级原型，以与模型无关的方式在存在数据异构性的客户端之间迁移知识。然而，现有方法通常直接从本地模型收集原型，由于客户端之间有偏的数据分布和不同的模型架构，这不可避免地会给表示学习带来不一致性。在本文中，我们发现统计异构性和模型异构性共同造成了表示不一致、分类器发散以及原型对齐偏斜的恶性循环，从而对客户端性能产生负面影响。为打破这一恶性循环，我们提出了一个名为 Federated Learning via Semantic Anchors（FedSA，基于语义锚点的联邦学习）的新颖框架，将原型生成与本地表示学习解耦。我们引入了一种新颖视角：使用简单而有效的语义锚点作为原型，引导本地模型学习一致的表示。通过引入语义锚点，我们进一步提出了结合间隔增强对比学习的基于锚点的正则化，以及基于锚点的分类器校准，以纠正跨客户端的特征提取器并校准分类器，在确保一致决策边界的同时实现原型的类内紧凑性和类间可分性。随后，我们利用这些一致且具有判别性的原型更新语义锚点，从而迭代地促使客户端协同学习具有鲁棒泛化能力的统一数据表示。在统计异构性和模型异构性设置下进行的大量实验表明，FedSA 在多种分类任务上显著优于现有的基于原型的 FL 方法。
英文摘要：
Prototype-based federated learning has emerged as a promising approach that shares lightweight prototypes to transfer knowledge among clients with data heterogeneity in a model-agnostic manner. However, existing methods often collect prototypes directly from local models, which inevitably introduce inconsistencies into representation learning due to the biased data distributions and differing model architectures among clients. In this paper, we identify that both statistical and model heterogeneity create a vicious cycle of representation inconsistency, classifier divergence, and skewed prototype alignment, which negatively impacts the performance of clients. To break the vicious cycle, we propose a novel framework named Federated Learning via Semantic Anchors (FedSA) to decouple the generation of prototypes from local representation learning. We introduce a novel perspective that uses simple yet effective semantic anchors serving as prototypes to guide local models in learning consistent representations. By incorporating semantic anchors, we further propose anchor-based regularization with margin-enhanced contrastive learning and anchor-based classifier calibration to correct feature extractors and calibrate classifiers across clients, achieving intra-class compactness and inter-class separability of prototypes while ensuring consistent decision boundaries. We then update the semantic anchors with these consistent and discriminative prototypes, which iteratively encourage clients to collaboratively learn a unified data representation with robust generalization. Extensive experiments under both statistical and model heterogeneity settings show that FedSA significantly outperforms existing prototype-based FL methods on various classification tasks.
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。
