arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.18409cs.LGcs.AIcs.LO
收藏

图神经网络统一表达力的方法

Unifying approach to uniform expressivity of graph neural networks

School of Computer Science, University of Sheffield, UK(谢菲尔德大学计算机科学学院);School of Computing Science, University of Glasgow, UK(格拉斯哥大学计算科学学院)

Huan Luo, Jonni Virtema

AI总结:

本文提出模板GNNs框架和Graded template modal logic逻辑,统一分析图神经网络的表达能力,并展示标准AC-GNNs及其变体作为T-GNNs的实例。

摘要:

图神经网络(GNNs)的表达能力通常通过与Weisfeiler-Leman(WL)算法和一阶逻辑片段的对应关系来分析。标准GNNs仅能对直接邻域或全局读取进行聚合。为了提高其表达能力,最近尝试将亚结构信息(例如循环计数和子图属性)纳入其中。在本文中,我们通过引入模板GNNs(T-GNNs),一种通用框架,其中节点特征通过从指定的图模板集中聚合有效的模板嵌入来更新。我们提出了一种相应的逻辑,即分级模板模态逻辑(GML(T)),以及基于模板的二义性与WL算法的一般概念。我们建立了T-GNNs的表达能力与GML(T)之间的等价性,并提供了一种统一分析GNN表达能力的方法:我们展示了标准AC-GNNs及其最近的变体如何被解释为T-GNNs的实例。

英文摘要:

The expressive power of Graph Neural Networks (GNNs) is often analysed via correspondence to the Weisfeiler-Leman (WL) algorithm and fragments of first-order logic. Standard GNNs are limited to performing aggregation over immediate neighbourhoods or over global read-outs. To increase their expressivity, recent attempts have been made to incorporate substructural information (e.g. cycle counts and subgraph properties). In this paper, we formalize this architectural trend by introducing Template GNNs (T-GNNs), a generalized framework where node features are updated by aggregating over valid template embeddings from a specified set of graph templates. We propose a corresponding logic, Graded template modal logic (GML(T)), and generalized notions of template-based bisimulation and WL algorithm. We establish an equivalence between the expressive power of T-GNNs and GML(T), and provide a unifying approach for analysing GNN expressivity: we show how standard AC-GNNs and its recent variants can be interpreted as instantiations of T-GNNs.

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。

↑