arXiv 2511.095992025-11-12cs.CV

FedeCouple：联邦学习中全局泛化性与局部适应性的细粒度平衡

FedeCouple: Fine-Grained Balancing of Global-Generalization and Local-Adaptability in Federated Learning

Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)（计算能力网络与信息安全部分省计算机科学中心，青岛科技大学（山东省科学院））；Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science（山东省工业网络与信息系统安全省重点实验室，山东省计算机科学基础研究中心）；School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院）；School of Computer Science and Cyber Engineering, Guangzhou University（广州大学计算机科学与网络工程学院）；State Key Lab. of Industrial Control Technology, Zhejiang University（浙江省工业控制技术重点实验室，浙江大学）

Ming Yang, Dongrun Li, Xin Wang, Feng Li, Lisheng Fan, Chunxiao Wang, Xiaoming Wu, Peng Cheng

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有解耦式个性化联邦学习存在组件耦合弱、性能受限的问题，提出FedeCouple方法，通过细粒度平衡全局泛化与局部适应，经理论验证收敛性，在多数据集上性能显著优于基线。

摘要：

在客户端数据异构的隐私保护移动网络传输场景下，将特征提取器与分类器解耦的个性化联邦学习方法已展现出提升学习能力的显著优势。然而，现有诸多方法主要聚焦于本地训练阶段的特征空间一致性与分类个性化，往往忽略了特征提取器的局部适应性以及分类器的全局泛化性。这一疏漏导致各组件间协调不足、耦合性弱，最终造成整体模型性能下降。为应对该挑战，我们提出FedeCouple，一种可在细粒度层面平衡全局泛化性与局部适应性的联邦学习方法。该方法联合学习全局与局部特征表示，同时采用动态知识蒸馏增强个性化分类器的泛化能力。我们进一步引入锚点优化特征空间，锚点严格的局部性与不可传输特性天然可保护隐私并降低通信开销。此外，我们通过理论分析证明，FedeCouple在非凸目标下可收敛，随着通信轮次增加，迭代结果会趋近于驻点。在五个图像分类数据集上开展的大量实验表明，FedeCouple在有效性、稳定性、可扩展性与安全性上均持续优于9种基线方法。值得注意的是，在有效性评估实验中，FedeCouple以4.3%的显著优势超越最优基线方法。

英文摘要：

In privacy-preserving mobile network transmission scenarios with heterogeneous client data, personalized federated learning methods that decouple feature extractors and classifiers have demonstrated notable advantages in enhancing learning capability. However, many existing approaches primarily focus on feature space consistency and classification personalization during local training, often neglecting the local adaptability of the extractor and the global generalization of the classifier. This oversight results in insufficient coordination and weak coupling between the components, ultimately degrading the overall model performance. To address this challenge, we propose FedeCouple, a federated learning method that balances global generalization and local adaptability at a fine-grained level. Our approach jointly learns global and local feature representations while employing dynamic knowledge distillation to enhance the generalization of personalized classifiers. We further introduce anchors to refine the feature space; their strict locality and non-transmission inherently preserve privacy and reduce communication overhead. Furthermore, we provide a theoretical analysis proving that FedeCouple converges for nonconvex objectives, with iterates approaching a stationary point as the number of communication rounds increases. Extensive experiments conducted on five image-classification datasets demonstrate that FedeCouple consistently outperforms nine baseline methods in effectiveness, stability, scalability, and security. Notably, in experiments evaluating effectiveness, FedeCouple surpasses the best baseline by a significant margin of 4.3%.

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。