A Meta-Learning Approach for Training Explainable Graph Neural Networks

In this article, we investigate the degree of explainability of graph neural networks (GNNs). The existing explainers work by finding global/local subgraphs to explain a prediction, but they are applied after a GNN has already been trained. Here, we propose a meta-explainer for improving the level o...

Full description

Bibliographic Details
Main Authors:	Scardapane, S. (Author), Spinelli, I. (Author), Uncini, A. (Author)
Format:	Article
Language:	English
Published:	Institute of Electrical and Electronics Engineers Inc. 2022
Subjects:	Adaptation models Classification (of information) Explainable artificial intelligence Explainable Artificial Intelligence (AI) Feature extraction Features extraction graph classification Graph classification Graph neural network graph neural network (GNN) Graph neural networks Graph theory Job analysis meta learning Metalearning node classification. Node classification. Optimisations Optimization Predictive models Task analysis Training
Online Access:	View Fulltext in Publisher

Internet

View Fulltext in Publisher

A Meta-Learning Approach for Training Explainable Graph Neural Networks

Internet

Similar Items