用双曲几何空间个性化建模异构图数据，提升联邦学习效果
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
- 将不同客户端数据嵌入定制化的洛伦兹空间，利用双曲几何特性
- 在低维设置下性能超越现有方法，尤其适合结构差异大的图数据
- 无需计算相似性或额外模块，直接聚合参数，效率更高
联邦学习实现隐私保护下的协作训练，但客户端数据高度异构仍是挑战，尤其在图联邦学习中，各客户端拥有结构各异的图。现有个性化联邦学习方法忽略真实图数据固有的几何特性。我们提出FlatLand，一种新型个性化联邦学习方法，将不同客户端的数据嵌入定制的双曲几何洛伦兹空间。核心洞察是：双曲几何天然适配真实图数据中普遍存在的负曲率，而洛伦兹空间中的类时间维度为编码客户端特异性提供了理论依据。我们设计参数解耦策略，将异构信息（由类时间参数捕获）与共性知识（保留在类空间参数中）分离，实现无需客户相似性估计和额外计算模块的直接聚合。在多种联邦图学习任务上的实验证明，FlatLand表现优异，尤其在低维设置下优势显著。
原文摘要 · Abstract (English)
Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph federated learning where clients possess structurally diverse graphs. Existing personalized federated learning (PFL) methods ignore the intrinsic geometric properties of diverse graph structures. We propose FlatLand, a novel personalized federated learning method that embeds different clients' data in tailored Lorentz space of hyperbolic geometry. Our key insight is that hyperbolic geometry naturally accommodates the intrinsic negative curvature prevalent in real-world graphs, while the time-like dimension in Lorentz space provides a principled way to encode client-specific heterogeneity. We develop a parameter decoupling strategy that separates heterogeneous information (captured in time-like parameters) from common knowledge (preserved in space-like parameters), enabling direct aggregation without requiring client similarity estimation and extra calculation modules. Empirical results on diverse federated graph learning tasks demonstrate that FlatLand achieves superior performance, particularly in low-dimensional settings.
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。