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.
@article{arxiv.2211.01548,
title = {INGREX: An Interactive Explanation Framework for Graph Neural Networks},
author = {Tien-Cuong Bui and Van-Duc Le and Wen-Syan Li and Sang Kyun Cha},
journal= {arXiv preprint arXiv:2211.01548},
year = {2022}
}
Comments
4 pages, 5 figures, This paper is under review for IEEE ICDE 2023