多域黎曼图粘合技术构建图基础模型

摘要

多领域图预训练通过整合来自不同领域的知识来提升目标领域性能，这对构建图基础模型至关重要。尽管已取得初步成功，但现有方案往往难以回答一个根本性问题：知识是如何跨领域整合或迁移的？这一理论局限促使我们重新思考模型预训练与领域适应之间的一致性和可迁移性。本文提出一种全新的黎曼几何视角，其核心思想是将任意图数据集融合为统一的平滑黎曼流形，从而系统化理解知识整合与迁移过程。为实现这一目标，我们的关键贡献是理论构建了神经流形粘合技术——首先通过自适应正交标架刻画局部几何特征，再将局部片段“粘合”为连贯整体。基于该理论，我们提出GraphGlue框架，支持基于指数移动平均原型的批量化预训练，并提供基于几何一致性的可迁移性度量。大量实验表明该框架在多种图领域均取得卓越性能。此外，我们通过实证验证了GraphGlue的几何缩放定律：更大规模的数据集能通过生成更平滑的流形来提升模型可迁移性。代码已开源于https://github.com/RiemannGraph/GraphGlue。

English

Multi-domain graph pre-training integrates knowledge from diverse domains to enhance performance in the target domains, which is crucial for building graph foundation models. Despite initial success, existing solutions often fall short of answering a fundamental question: how is knowledge integrated or transferred across domains? This theoretical limitation motivates us to rethink the consistency and transferability between model pre-training and domain adaptation. In this paper, we propose a fresh Riemannian geometry perspective, whose core idea is to merge any graph dataset into a unified, smooth Riemannian manifold, enabling a systematic understanding of knowledge integration and transfer. To achieve this, our key contribution is the theoretical establishment of neural manifold gluing, which first characterizes local geometry using an adaptive orthogonal frame and then "glues" the local pieces together into a coherent whole. Building on this theory, we present the GraphGlue framework, which supports batched pre-training with EMA prototyping and provides a transferability measure based on geometric consistence. Extensive experiments demonstrate its superior performance across diverse graph domains. Moreover, we empirically validated GraphGlue's geometric scaling law, showing that larger quantities of datasets improve model transferability by producing a smoother manifold. Codes are available at https://github.com/RiemannGraph/GraphGlue.

多域黎曼图粘合技术构建图基础模型

Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models

摘要

Support