Saved in:
Bibliographic Details
Main Authors: Yue, Xiao, Qu, Guangzhi, Gan, Lige
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.06352
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909796666441728
author Yue, Xiao
Qu, Guangzhi
Gan, Lige
author_facet Yue, Xiao
Qu, Guangzhi
Gan, Lige
contents One significant challenge of exploiting Graph neural networks (GNNs) in real-life scenarios is that they are always treated as black boxes, therefore leading to the requirement of interpretability. To address this, model-level interpretation methods have been developed to explain what patterns maximize probability of predicting to a certain class. However, existing model-level interpretation methods pose several limitations such as generating invalid explanation graphs and lacking reliability. In this paper, we propose a new Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks (GIN-Graph), to generate reliable and high-quality model-level explanation graphs. The implicit and likelihood-free generative adversarial networks are exploited to construct the explanation graphs which are similar to original graphs, meanwhile maximizing the prediction probability for a certain class by adopting a novel objective function for generator with dynamic loss weight scheme. Experimental results indicate that GIN-Graph can be applied to interpret GNNs trained on a variety of graph datasets and generate high-quality explanation graphs with high stability and reliability.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06352
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks
Yue, Xiao
Qu, Guangzhi
Gan, Lige
Machine Learning
One significant challenge of exploiting Graph neural networks (GNNs) in real-life scenarios is that they are always treated as black boxes, therefore leading to the requirement of interpretability. To address this, model-level interpretation methods have been developed to explain what patterns maximize probability of predicting to a certain class. However, existing model-level interpretation methods pose several limitations such as generating invalid explanation graphs and lacking reliability. In this paper, we propose a new Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks (GIN-Graph), to generate reliable and high-quality model-level explanation graphs. The implicit and likelihood-free generative adversarial networks are exploited to construct the explanation graphs which are similar to original graphs, meanwhile maximizing the prediction probability for a certain class by adopting a novel objective function for generator with dynamic loss weight scheme. Experimental results indicate that GIN-Graph can be applied to interpret GNNs trained on a variety of graph datasets and generate high-quality explanation graphs with high stability and reliability.
title GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2503.06352