用几何基统一图结构，实现跨域图模型的高效迁移。
Structure-Centric Graph Foundation Model via Geometric Bases
- 将图拓扑视为核心知识，构建共享几何坐标系
- 通过格罗莫夫-沃瑟斯坦距离对齐结构，支持异构图兼容
- 无需固定特征维度，可适配不同数据集的特征空间
图基础模型（GFMs）旨在跨图领域获得可迁移表示，但受限于结构异质性与不兼容的节点特征空间。本文提出结构中心的图基础模型（SCGFM），将图拓扑作为可迁移知识的主要来源。通过将图建模为度量测度空间，SCGFM引入可学习的几何基，定义共享的结构坐标系。利用格罗莫夫-沃瑟斯坦距离将图对齐至这些基，生成结构对齐的潜在表示，可适应异构图拓扑。为解决特征不兼容问题，SCGFM采用结构感知的特征重编码机制，无需固定特征维度或特定数据集预处理即可统一节点表示。在图级和节点级任务上的实验表明，该方法在域内与跨域泛化上均优于现有GFM方法。
原文摘要 · Abstract (English)
Graph foundation models (GFMs) seek transferable representations across graph domains but are limited by structural heterogeneity and incompatible node feature spaces. We propose Structure-Centric Graph Foundation Models (SCGFM), which treat graph topology as the primary source of transferable knowledge. Modeling graphs as metric measure spaces, SCGFM introduces learnable geometric bases that define a shared structural coordinate system. Graphs are aligned to these bases via Gromov-Wasserstein distances, yielding structure-aligned latent representations that accommodate heterogeneous graph topologies. To address feature incompatibility, SCGFM employs a structure-aware feature re-encoding mechanism that unifies node representations without assuming a fixed feature dimensionality or requiring dataset-specific preprocessing. Experiments on graph- and node-level tasks demonstrate strong in-domain and cross-domain generalization, outperforming existing GFM approaches.
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。