Saved in:
Bibliographic Details
Main Authors: Zhang, Ding, Betala, Siddharth, Agarwal, Chirag
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.07708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910015439241216
author Zhang, Ding
Betala, Siddharth
Agarwal, Chirag
author_facet Zhang, Ding
Betala, Siddharth
Agarwal, Chirag
contents Evaluating the quality of post-hoc explanations for Graph Neural Networks (GNNs) remains a significant challenge. While recent years have seen an increasing development of explainability methods, current evaluation metrics (e.g., fidelity, sparsity) often fail to assess whether an explanation identifies the true underlying causal variables. To address this, we propose the Explanation-Generalization Score (EGS), a metric that quantifies the causal relevance of GNN explanations. EGS is founded on the principle of feature invariance and posits that if an explanation captures true causal drivers, it should lead to stable predictions across distribution shifts. To quantify this, we introduce a framework that trains GNNs using explanatory subgraphs and evaluates their performance in Out-of-Distribution (OOD) settings (here, OOD generalization serves as a rigorous proxy for the explanation's causal validity). Through large-scale validation involving 11,200 model combinations across synthetic and real-world datasets, our results demonstrate that EGS provides a principled benchmark for ranking explainers based on their ability to capture causal substructures, offering a robust alternative to traditional fidelity-based metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07708
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalization
Zhang, Ding
Betala, Siddharth
Agarwal, Chirag
Machine Learning
Evaluating the quality of post-hoc explanations for Graph Neural Networks (GNNs) remains a significant challenge. While recent years have seen an increasing development of explainability methods, current evaluation metrics (e.g., fidelity, sparsity) often fail to assess whether an explanation identifies the true underlying causal variables. To address this, we propose the Explanation-Generalization Score (EGS), a metric that quantifies the causal relevance of GNN explanations. EGS is founded on the principle of feature invariance and posits that if an explanation captures true causal drivers, it should lead to stable predictions across distribution shifts. To quantify this, we introduce a framework that trains GNNs using explanatory subgraphs and evaluates their performance in Out-of-Distribution (OOD) settings (here, OOD generalization serves as a rigorous proxy for the explanation's causal validity). Through large-scale validation involving 11,200 model combinations across synthetic and real-world datasets, our results demonstrate that EGS provides a principled benchmark for ranking explainers based on their ability to capture causal substructures, offering a robust alternative to traditional fidelity-based metrics.
title Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalization
topic Machine Learning
url https://arxiv.org/abs/2602.07708