The Expressive Power of Graph Neural Networks: A Survey

被引：0

作者：

Zhang, Bingxu ^{[1
]}

Fan, Changjun ^{[1
]}

Liu, Shixuan ^{[1
]}

Huang, Kuihua ^{[1
]}

Zhao, Xiang ^{[1
]}

Huang, Jincai ^{[1
]}

Liu, Zhong ^{[1
]}

机构：

[1] Natl Univ Def Technol, Coll Syst Engn, Lab Big Data & Decis, Changsha 410073, Hunan, Peoples R China

来源：

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING | 2025年 / 37卷 / 03期

基金：

中国国家自然科学基金;

关键词：

Topology; Feature extraction; Data models; Surveys; Message passing; Graph neural networks; Fans; Encoding; Artificial neural networks; Vectors; Approximation ability; expressive power; graph neural network; separation ability;

D O I：

10.1109/TKDE.2024.3523700

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power. Early works in this domain mainly focus on studying the graph isomorphism recognition ability of GNNs, and recent works try to leverage the properties such as subgraph counting and connectivity learning to characterize the expressive power of GNNs, which are more practical and closer to real-world. However, no survey papers and open-source repositories comprehensively summarize and discuss models in this important direction. To fill the gap, we conduct a first survey for models for enhancing expressive power under different forms of definition. Concretely, the models are reviewed based on three categories, i.e., Graph feature enhancement, Graph topology enhancement, and GNNs architecture enhancement.

引用

页码：1455 / 1474

页数：20