arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.04244cs.LG
收藏

GraphVec:跨域图向量化解构用于图级表示学习

GraphVec: Cross-Domain Graph Vectorization for Graph-Level Representation Learning

School of Data Science(数据科学学院)

Qi Feng, Jicong Fan

AI总结:

GraphVec通过构建多尺度全局图并提取谱嵌入,实现跨域图表示学习,其结合GIN-图Transformer和多层参考分布模块,提升节点分布信息,实验表明在跨域少样本图分类和聚类中优于基线模型。

摘要:

学习跨异构域的通用图表示具有挑战性,因为图数据集在拓扑、节点属性语义、特征维度和属性可用性上存在差异。我们提出了GraphVec,一种无需语言模型的图向量化模型,将多样化的图映射到可转移的固定维度嵌入中用于图级任务。替代直接使用不可比的原始节点属性,GraphVec在每个数据集上构建多尺度全局图,并提取谱嵌入以获得领域无关的关系特征。为使这些谱特征在不同数据集中具有可比性,我们引入了基于正交变换的密度最大化均值对齐算法,并证明其单调收敛性。GraphVec进一步结合了GIN-图Transformer主干和多层参考分布模块,该模块保留了超出标准池化标准的节点级分布信息。我们还为所提出的模型提供了泛化误差界。在13个数据集上进行的实验表明,GraphVec在跨域少样本图分类和图聚类中一致优于强大的图预训练基线。除了图级任务外,GraphVec还产生了强大的节点级表示,在少样本节点分类中与代表性图提示学习方法竞争性表现。

英文摘要:

Learning universal graph representations across heterogeneous domains is difficult because graph datasets differ in topology, node-attribute semantics, feature dimensions, and even attribute availability. We propose GraphVec, a language-model-free graph vectorization model that maps diverse graphs into transferable fixed-dimensional embeddings for graph-level tasks. Instead of directly using incomparable raw node attributes, GraphVec constructs multi-scale global graphs over all nodes in each dataset and extracts spectral embeddings to obtain domain-agnostic relational features. To make these spectral features comparable across datasets, we introduce a density-maximization mean alignment algorithm over orthogonal transformations and prove its monotonic convergence. GraphVec further combines a GIN--Graph Transformer backbone with a multi-layer reference distribution module, which preserves node-level distributional information beyond standard pooling. We also provide a generalization error bound for the proposed model. Experiments on 13 datasets with more than 15 comparison methods demonstrate that GraphVec consistently outperforms strong graph pretraining baselines in cross-domain few-shot graph classification and graph clustering. Beyond graph-level tasks, GraphVec also yields strong node-level representations, achieving competitive performance on few-shot node classification against representative graph prompt learning methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑