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

February 28, 2026

作者: Li Sun, Zhenhao Huang, Silei Chen, Lanxu Yang, Junda Ye, Sen Su, Philip S. Yu

cs.AI

摘要

多領域圖預訓練通過整合來自不同領域的知識來提升目標領域的性能，這對於構建圖基礎模型至關重要。儘管已取得初步成功，但現有解決方案往往難以回答一個根本性問題：知識是如何跨領域整合或遷移的？這一理論侷限性促使我們重新思考模型預訓練與領域適應之間的一致性和可遷移性。本文提出了一種全新的黎曼幾何視角，其核心思想是將任意圖數據集合併到統一、光滑的黎曼流形中，從而實現對知識整合與遷移的系統性理解。為實現這一目標，我們的關鍵貢獻是理論上建立了神經流形粘合技術——首先通過自適應正交標架表徵局部幾何特徵，再將局部片段「粘合」成連貫的整體。基於該理論，我們提出了GraphGlue框架，該框架支持帶有指數移動平均原型生成的批量預訓練，並提供基於幾何一致性的可遷移性度量。大量實驗表明該框架在多樣化圖領域中均表現出卓越性能。此外，我們通過實證驗證了GraphGlue的幾何尺度定律，證明更大規模的數據集能通過生成更光滑的流形來提升模型可遷移性。代碼已開源於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.