.png){kind=icon}
返回
Higher-Order Interaction Goes Neural: A Substructure Assembling Graph Attention Network for Graph Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2021.3105544.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph classification has been widely used for knowledge discovery in numerous practical application scenarios, such as social networks and protein-protein interaction networks. Recently, Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in graph classification. However, existing GNN models mainly focus on capturing the information of immediate or first-order neighboring nodes within a single layer. The graph substructure and substructure interaction, which plays an important role in learning graph representations, are usually overlooked. In this paper, we propose a Substructure Assembling Graph Attention Network (SA-GAT) to extract graph features and improve the performance of graph classification. SA-GAT is able to fully explore higher-order substructure information hidden in graphs by a core module called Substructure Interaction Attention (SIA), which takes both the information of neighbors' substructures and the interaction information among them into account during aggregation process. Theoretically, we have also proved that SA-GAT satisfies the graph isomorphism theory of graph neural network design, which is that the network should map isomorphic graphs to the same representation and output the same prediction. Extensive experimental results on multiple real-world graph classification datasets demonstrate that the proposed SA-GAT outperforms the state-of-the-art methods including graph kernels and graph neural networks.
Keyword:
Kernel
Graph neural networks
Aggregates
Task analysis
Feature extraction
Proteins
Knowledge discovery
Graph classification
graph attention networks
higher-order graph
Index Terms
substructure interaction
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
分享收藏Admixture Effects on the Rheological/Mechanical Behavior and Micro-Structure Evolution of Alkali-Activated Slag Backfills.png)
Minerals
OAAI
MineralsIF0
OAAI分享收藏Matrix Metalloproteinase-9 Is Involved in Chronic Lymphocytic Leukemia Cell Response to Fludarabine and Arsenic TrioxidePLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏A graph kernel based on context vectors for extracting drug-drug interactions基于上下文向量的图核，用于提取药物-药物相互作用OAAI
OAAI分享收藏Anomeric specificity of glucose effect on cAMP, fructose 1,6-bisphosphatase, and trehalase in yeast
PREAI
分享收藏
查看更多内容