提出R-GFM，让图模型自动适应不同尺度结构。
Learning Graph Foundation Models on Riemannian Graph-of-Graphs
- 用黎曼流形构建多尺度图中图结构，动态捕捉不同层级关系。
- 在多个下游任务上实现最高性能，相对提升达49%。
- 适合需要跨尺度建模的复杂图分析场景。
图基础模型（GFMs）通过在大规模图数据上预训练，已改变图机器学习格局，支持跨多样任务与领域的通用推理。现有GFMs采用固定跳数子图采样，导致感受野固定，在面对需异构且未知结构上下文的任务时出现尺度不匹配。本文提出R-GFM，基于黎曼流形的图中图（GoG）框架，将结构尺度作为建模核心要素。R-GFM在不同跳数下过采样子图，构建多尺度GoG，并从黎曼流形中学习几何自适应表示。理论分析表明，相比固定尺度模型，R-GFM能降低结构域泛化误差。在多个数据集上的实验显示，其在下游任务中达到最优表现，相对提升最高达49%。代码已开源：https://github.com/USTC-DataDarknessLab/R-GFM。
原文摘要 · Abstract (English)
Graph foundation models (GFMs), pretrained on massive graph data, have transformed graph machine learning by supporting general-purpose reasoning across diverse graph tasks and domains. Existing GFMs pretrained with fixed-hop subgraph sampling impose a fixed receptive field, causing scale mismatch on diverse tasks, which often require heterogeneous and unknown structural contexts beyond a fixed sampling scale. We propose R-GFM, a Riemannian Graph-of-Graphs (GoG) based foundation model, that treats structural scale as a first-class citizen in modeling. R-GFM constructs a multi-scale GoG over-sampled subgraphs at different hop distances and learns geometry-adaptive representations from Riemannian manifolds. Theoretical analysis shows that R-GFM reduces structural domain generalization error compared to fixed-scale GFMs. Experiments on various datasets demonstrate that R-GFM achieves state-of-the-art performance, with up to a 49% relative improvement on downstream tasks. Our code is available at https://github.com/USTC-DataDarknessLab/R-GFM.
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。