研究人员开发了一个名为解耦关系子空间对齐（DRSA）的新框架，以提高图基础模型（GFMs）在复杂、多域异构图上的性能。现有方法在不同数据类型之间的特征偏移和关系差距方面存在困难，导致了“类型塌陷”等问题。DRSA通过将特征语义与关系结构解耦，使用双关系子空间投影和特征-结构解耦表示来更好地处理变化并增强跨域知识迁移。 AI
影响 增强了图基础模型的跨域和少样本知识迁移能力，有望提高在复杂真实世界数据集上的性能。
排序理由 这是一篇详细介绍图基础模型新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.04594v1 Announce Type: new Abstract: Many real-world heterogeneous graphs exhibit pronounced heterophily, where connected nodes often have dissimilar labels or play different semantic roles. In such settings, standard heterogeneous graph neural networks that aggregate …
arXiv:2605.00731v1 Announce Type: cross Abstract: While Graph Foundation Models (GFMs) have achieved remarkable success in homogeneous graphs, extending them to multi-domain heterogeneous graphs (MDHGs) remains a formidable challenge due to cross-type feature shifts and intra-dom…
While Graph Foundation Models (GFMs) have achieved remarkable success in homogeneous graphs, extending them to multi-domain heterogeneous graphs (MDHGs) remains a formidable challenge due to cross-type feature shifts and intra-domain relation gaps. Existing global feature alignme…