GraphXAIN: Narratives to Explain Graph Neural Networks

TL;DR

GraphXAIN introduces a novel approach that uses Large Language Models to generate natural language narratives explaining GNN predictions, making explanations more understandable for non-experts.

Contribution

It is the first method to translate GNN explanations into coherent narratives using LLMs, enhancing interpretability and user satisfaction.

Findings

Improves understandability, satisfaction, and convincingness of GNN explanations.

95% of users found GraphXAIN valuable for explanations.

Enhances trustworthiness and usability when combined with other explainers.

Abstract

Graph Neural Networks (GNNs) are a powerful technique for machine learning on graph-structured data, yet they pose challenges in interpretability. Existing GNN explanation methods usually yield technical outputs, such as subgraphs and feature importance scores, that are difficult for non-data scientists to understand and thereby violate the purpose of explanations. Motivated by recent Explainable AI (XAI) research, we propose GraphXAIN, a method that generates natural language narratives explaining GNN predictions. GraphXAIN is a model- and explainer-agnostic method that uses Large Language Models (LLMs) to translate explanatory subgraphs and feature importance scores into coherent, story-like explanations of GNN decision-making processes. Evaluations on real-world datasets demonstrate GraphXAIN's ability to improve graph explanations. A survey of machine learning researchers and practitioners reveals that GraphXAIN enhances four explainability dimensions: understandability, satisfaction, convincingness, and suitability for communicating model predictions. When combined with another graph explainer method, GraphXAIN further improves trustworthiness, insightfulness, confidence, and usability. Notably, 95% of participants found GraphXAIN to be a valuable addition to the GNN explanation method. By incorporating natural language narratives, our approach serves both graph practitioners and non-expert users by providing clearer and more effective explanations.