发表机构
The Chinese University of Hong Kong; Yale University; Huawei Technologies Co., Ltd.; The Hong Kong University of Science and Technology (Guangzhou)（香港中文大学; 耶鲁大学; 华为技术有限公司; 香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对图联邦学习中客户端图结构异质性问题，提出FlatLand方法，通过定制洛伦兹空间与参数解耦策略实现个性化联邦学习，在低维设置下表现更优。
AI 中文摘要
联邦学习支持隐私保护的协同训练，但客户端数据高度异质性仍是挑战，尤其在客户端拥有结构多样图的图联邦学习场景中。现有个性化联邦学习（PFL）方法忽略了多样图结构的内在几何特性。我们提出FlatLand，一种新颖的个性化联邦学习方法，将不同客户端的数据嵌入到双曲几何的定制洛伦兹空间中。核心见解是，双曲几何可自然适配真实图中普遍存在的内在负曲率，而洛伦兹空间中的类时维度为编码客户端特定异质性提供了有原则的方式。我们开发了一种参数解耦策略，将异质信息（由类时参数捕获）与通用知识（由类空参数保留）分离，无需客户端相似度估计和额外计算模块即可直接聚合。在多样的联邦图学习任务上的实验结果表明，FlatLand实现了更优的性能，尤其在低维设置下表现突出。
英文摘要
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.
Comments34 pages, 9 figures, 8 tables. Accepted at ICML 2026 (Oral)
