.png){kind=icon}
返回
Kernel entropy graph isomorphism network for graph classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113182.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• We propose a fusion method for graph neural networks and graph kernels based on the attention mechanism. • We use a shortest path matching kernel to extract global structural features of graph. • We adopt an entropy-based graph isomorphism network to extract local structural features of graph. • We utilize the Nystom method kernel matrix for reduced-rank decomposition, which reduces the time consumed for model computation.
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Local kernels based graph learning for multiple kernel clustering基于局部核的多核聚类图学习.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
Evolutionary structure learning on temporal networks using von Neumann entropy基于von Neumann熵的时序网络演化结构学习PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏GL-BKGNN: Graphlet-based Bi-Kernel Interpretable Graph Neural NetworksGL-BKGNN：基于图模的Bi-Kernel可解释图神经网络INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏GNN-LoFI: A novel graph neural network through localized feature-based histogram intersectionPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏分享收藏
查看更多内容