Edge-Level Explanations for Graph Neural Networks by Extending Explainability Methods for Convolutional Neural Networks
Authors:
- 1 November 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 249-252
Abstract
Graph Neural Networks (GNNs) are deep learning models that take graph data as inputs, and they are applied to various tasks such as traffic prediction and molecular property prediction. However, owing to the complexity of the GNNs, it has been difficult to analyze which parts of inputs affect the GNN model’s outputs. In this study, we extend explainability methods for Convolutional Neural Networks (CNNs), such as Local Interpretable Model-Agnostic Explanations (LIME), Gradient-Based Saliency Maps, and Gradient-Weighted Class Activation Mapping (Grad-CAM) to GNNs, and predict which edges in the input graphs are important for GNN decisions. The experimental results indicate that the LIME-based approach is the most efficient explainability method for multiple tasks in the real-world situation, outperforming even the state-of-the-art method in GNN explainability.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- A Comprehensive Survey on Graph Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2020
- Explainability Methods for Graph Convolutional Neural Networks2019
- Methods for interpreting and understanding deep neural networksDigital Signal Processing, 2018
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017
- "Why Should I Trust You?"2016
- Quantum chemistry structures and properties of 134 kilo moleculesScientific Data, 2014
- Automating the Construction of Internet Portals with Machine LearningInformation Retrieval Journal, 2000
- Regression Shrinkage and Selection Via the LassoJournal of the Royal Statistical Society Series B: Statistical Methodology, 1996