INGREX: An Interactive Explanation Framework for Graph Neural Networks

TL;DR

INGREX is an interactive framework that enhances understanding of GNN predictions by integrating multiple explanation algorithms, addressing the limitations of static explanations in complex models.

Contribution

This paper introduces INGREX, a novel interactive explanation framework for GNNs that combines various algorithms to improve interpretability and user comprehension.

Findings

Effective in three different explanation scenarios

Enhances user understanding of GNN predictions

Integrates multiple explanation algorithms

Abstract

Graph Neural Networks (GNNs) are widely used in many modern applications, necessitating explanations for their decisions. However, the complexity of GNNs makes it difficult to explain predictions. Even though several methods have been proposed lately, they can only provide simple and static explanations, which are difficult for users to understand in many scenarios. Therefore, we introduce INGREX, an interactive explanation framework for GNNs designed to aid users in comprehending model predictions. Our framework is implemented based on multiple explanation algorithms and advanced libraries. We demonstrate our framework in three scenarios covering common demands for GNN explanations to present its effectiveness and helpfulness.