提出视图空间概念，实现跨异构图的统一表示学习
View Space: Learning Representation across Arbitrary Graphs
- 引入视图空间概念，利用图结构构建跨图统一表征
- 在27个基准上超越现有模型8.93%，优于12个调优GNN至少3.30%
- 适合需要跨数据集泛化的图学习研究者使用
将预训练模型泛化到未见数据集而不重新训练，是迈向基础模型的核心挑战。由于不同数据集间特征维度和语义差异巨大，对数值型数据实现完全归纳推理尤为困难。我们观察到，在存在图结构的情况下，数值型数据具有超越特征空间的独特结构诱导表示轴，称为视图空间。该视图空间实现了异构特征图的统一表示，并启发了图视图变换（GVT）这一可跨任意图共享的参数化映射框架。我们以递归式GVT为例，构建了一个完全归纳的节点表征学习架构，用于节点分类任务。该模型在OGBN-Arxiv上预训练，评估于27个基准上，相比先前的完全归纳图模型GraphAny提升8.93%，且优于12个单独调优的GNN模型至少3.30%。这些结果确立了视图空间作为异构特征空间中跨图学习的原理性与实用性基础。代码与模型检查点已开源。
原文摘要 · Abstract (English)
Generalizing pretrained models to unseen datasets without retraining is a central challenge toward foundation models. Achieving fully inductive inference on numerical data is particularly difficult due to large variations in feature dimensionality and semantics across datasets. We observe that, in the presence of graph structure, numerical data admits a distinct structure-induced representational axis beyond the feature space, which we formalize as the view space. This view space enables a unified representation of graphs with heterogeneous features and motivates Graph View Transformation (GVT), a class of parametric mappings that can be shared across arbitrary graphs. We instantiate this framework with Recurrent GVT, an architecture for fully inductive node representation learning in node classification. Pretrained on OGBN-Arxiv and evaluated on 27 benchmarks, Recurrent GVT outperforms GraphAny, the prior fully inductive graph model, by +8.93%, and surpasses 12 individually tuned GNNs by at least +3.30%. These results establish the view space as a principled and practical foundation for learning across graphs with heterogeneous feature spaces. Code and checkpoints are available in https://github.com/dooho00/graph-view-space.
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。