AI 中文总结
本研究提炼出跨领域图特征统一的四项要求，提出基于拓扑感知滑动窗口特征编码与生成式重构的图基础模型SliGFM，以实现异质节点特征的有效统一与跨领域知识迁移。
AI 中文摘要
图基础模型（Graph Foundation Models, GFMs）是近期兴起的通用图学习范式，旨在学习可跨不同图领域及下游任务迁移的可复用知识，减少特定模型开发的需求。实现该目标需协调各领域间节点特征、图结构及语义信息的显著异质性，其中异质节点特征是输入层面的基础障碍，其维度与语义在不同数据集间差异巨大。现有研究通常将异质节点特征投影或映射到固定维度空间，常隐含将维度一致性等同于有效特征统一，但仅维度一致性无法保证统一特征保留有价值语义、捕捉可支持跨领域知识迁移的可迁移模式。为弥合这一概念差距，本研究提炼出跨领域图特征统一的四项要求：形式统一性、跨领域可迁移性、信息保留性及主干兼容性。遵循这些原则，本研究提出SliGFM，一种基于拓扑感知滑动窗口特征编码与生成式重构的图基础模型；SliGFM按拓扑平滑度对特征维度排序，并用共享滑动窗口特征编码器扫描重排后的特征，将异质特征转换为有序固定维度特征标记的公共空间，该公式使平滑度感知Transformer能捕捉每个节点内特征标记间的可迁移关系模式，而生成式重构目标则鼓励保留原始特征信息。
英文摘要
Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for general-purpose graph learning, aiming to learn reusable knowledge that generalizes across diverse graph domains and downstream tasks, reducing the need for specific model development. Achieving this goal requires reconciling the substantial heterogeneity in node features, graph structures, and semantic information across domains. Among them, heterogeneous node features constitute a fundamental input-level barrier, as their dimensionality and semantics vary substantially across datasets. Existing studies typically project or map heterogeneous node features into a fixed-dimensional space, often implicitly equating dimensional uniformity with effective feature unification. Yet dimensional consistency alone does not ensure that the unified features preserve informative semantics and capture transferable patterns that can support cross-domain knowledge transfer. To bridge this conceptual gap, we distill four desiderata for cross-domain graph feature unification: formal uniformity, cross-domain transferability, information preservation, and backbone compatibility. Guided by these principles, we propose SliGFM, a graph foundation model built upon topology-aware sliding-window feature encoding and generative reconstruction. SliGFM orders feature dimensions by topological smoothness and scans the reordered features with a shared sliding-window feature encoder, transforming heterogeneous features into a common space of ordered fixed-dimensional feature tokens. This formulation enables a smoothness-aware transformer to capture transferable relational patterns among feature tokens within each node, while the generative reconstruction objective encourages preservation of the original feature information.
