Learning model-level explanations of graph neural networks via subgraph order embedding space

Li Liu; Pengyu Wan; F. Z. Zhang; Youmin Zhang; Qun Liu; Guoyin Wang

doi:10.1016/j.neunet.2025.107815

ScienceGate Book Chapters

JOURNAL ARTICLE

Learning model-level explanations of graph neural networks via subgraph order embedding space

Li Liu Pengyu Wan F. Z. Zhang Youmin Zhang Qun Liu Guoyin Wang

Year: 2025 Journal: Neural Networks Vol: 191 Pages: 107815-107815 Publisher: Elsevier BV

DOI: 10.1016/j.neunet.2025.107815

Get Full-Text PDF Get Analytical Report

Keywords:

Induced subgraph isomorphism problem Embedding Subgraph isomorphism problem Artificial neural network Space (punctuation) Computer science Graph Artificial intelligence Order (exchange) Theoretical computer science Mathematics Line graph Voltage graph

Metrics

Cited By

0.00

FWCI (Field Weighted Citation Impact)

Refs

0.10

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Topics

Advanced Graph Neural Networks

Physical Sciences → Computer Science → Artificial Intelligence

Topic Modeling

Physical Sciences → Computer Science → Artificial Intelligence

Graph Theory and Algorithms

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Learning model-level explanations of graph neural networks via subgraph order embedding space

Metrics

Topics

Related Documents

SUPExplainer: Subgraph-Level Explanations for Graph Neural Networks via Reinforcement Learning Mechanism

XGNN: Towards Model-Level Explanations of Graph Neural Networks

Exploiting Local Information with Subgraph Embedding for Graph Neural Networks

PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks

Subgraph Pattern Neural Networks for High-Order Graph Evolution Prediction