SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods
arXiv:2106.08532 · doi:10.54364/AAIML.2023.1168
Abstract
Explaining the foundations for predictions obtained from graph neural networks (GNNs) is critical for credible use of GNN models for real-world problems. Owing to the rapid growth of GNN applications, recent progress in explaining predictions from GNNs, such as sensitivity analysis, perturbation methods, and attribution methods, showed great opportunities and possibilities for explaining GNN predictions. In this study, we propose a method to improve the explanation quality of node classification tasks that can be applied in a post hoc manner through aggregation of auxiliary explanations from important neighboring nodes, named SEEN. Applying SEEN does not require modification of a graph and can be used with diverse explainability techniques due to its independent mechanism. Experiments on matching motif-participating nodes from a given graph show great improvement in explanation accuracy of up to 12.71% and demonstrate the correlation between the auxiliary explanations and the enhanced explanation accuracy through leveraging their contributions. SEEN provides a simple but effective method to enhance the explanation quality of GNN model outputs, and this method is applicable in combination with most explainability techniques.
arXiv comment15 pages, 3 figures
References in corpus (11)
- Neural Message Passing for Quantum Chemistry
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- Learning Important Features Through Propagating Activation Differences
- Convolutional Networks on Graphs for Learning Molecular Fingerprints
- GNNExplainer: Generating Explanations for Graph Neural Networks
- Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
- SimplE Embedding for Link Prediction in Knowledge Graphs
- Higher-Order Explanations of Graph Neural Networks via Relevant Walks
- Parameterized Explainer for Graph Neural Network
- Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models
- PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks