SCGFM-ART：面向结构中心图基础模型的摊销关系传输
SCGFM-ART: Amortized Relational Transport for Structure-Centric Graph Foundation Models
- University of Electronic Science and Technology of China（电子科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出SCGFM-ART框架，通过摊销关系传输将任意图对齐到共享关系图谱，实现跨域图表示学习，在14个任务上取得最优迁移性能，并大幅加速推理。
AI中文摘要：
图基础模型（GFMs）旨在跨严重异质的图域学习可迁移的表示。然而，拓扑、图规模和特征语义方面的严重域偏移阻碍了统一、与域无关的表示空间的构建。为解决此问题，我们提出SCGFM-ART，一种结构中心的GFM框架，通过摊销关系传输（ART）将任意图对齐到共享的关系图谱上。关系图谱作为一个由有限关系地标（基）定义的通用坐标系，而ART直接预测可复用的、端到端的图到基传输计划，绕过了昂贵的运行时Gromov-Wasserstein优化。在此公式下，SCGFM-ART将图分解为统一表示：全局上通过其相对于图谱的关系响应坐标，局部上通过其节点到角色的结构对应关系。这些对应关系将不同的节点属性投影到规范角色空间，在单一对齐界面内解决结构和语义异质性。通过将图和图谱基严格建模为有限度量关系空间，我们建立了坐标保真度界限，证明了在预测传输计划下的稳定性，并推导出摊销覆盖界限，保证我们的学习目标紧密替代理想的关系覆盖。在14个跨域图级和节点级分类任务上进行基准测试，SCGFM-ART实现了最先进的迁移性，分别获得了2.29和1.14的优异平均排名。拓扑扰动分析表明，节点角色传输保留了全局坐标之外的细粒度结构细微差别。在真实世界基准上，摊销公式通过避免测试时的迭代对齐，实现了44.2至85.1倍的冻结目标域推理加速。
英文摘要：
Graph foundation models (GFMs) aim to learn transferable representations across severely heterogeneous graph domains. However, severe domain shifts in topology, graph scale, and feature semantics impede the construction of a unified, domain-agnostic representation space. To address this, we propose SCGFM-ART, a structure-centric GFM framework that aligns arbitrary graphs onto a shared relational atlas via Amortized Relational Transport (ART). The relational atlas serves as a universal coordinate system defined by a finite set of relational landmarks (bases), while ART directly predicts reusable, end-to-end graph-to-base transport plans, bypassing costly runtime Gromov-Wasserstein optimizations. Under this formulation, SCGFM-ART decomposes a graph into a unified representation: globally via its relational response coordinates relative to the atlas, and locally via its node-to-role structural correspondences. These correspondences project disparate node attributes into a canonical role space, resolving structural and semantic heterogeneity within a singular alignment interface. Rigorously modeling graphs and atlas bases as finite measured relational spaces, we establish coordinate fidelity bounds, prove stability under predicted transport plans, and derive an amortized coverage bound that guarantees our learning objective tightly surrogates ideal relational coverage. Benchmarked across 14 cross-domain graph- and node-level classification tasks, SCGFM-ART achieves state-of-the-art transferability, securing superior average ranks of 2.29 and 1.14, respectively. Topological perturbation analyses demonstrate that node-role transport retains fine-grained structural nuances beyond global coordinates. On real-world benchmarks, the amortized formulation yields 44.2 to 85.1 times faster frozen target-domain inference by avoiding iterative alignment at test time.
