Towards Automated Evaluation of Explanations in Graph Neural Networks
arXiv:2106.11864
Abstract
Explaining Graph Neural Networks predictions to end users of AI applications in easily understandable terms remains an unsolved problem. In particular, we do not have well developed methods for automatically evaluating explanations, in ways that are closer to how users consume those explanations. Based on recent application trends and our own experiences in real world problems, we propose automatic evaluation approaches for GNN Explanations.
5 pages, 4 figures, XAI Workshop at ICML 2021
References in corpus (7)
- Variational Graph Auto-Encoders
- Snorkel: Rapid Training Data Creation with Weak Supervision
- Parameterized Explainer for Graph Neural Network
- On Explainability of Graph Neural Networks via Subgraph Explorations
- Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
- Graph Neural Network to Dilute Outliers for Refactoring Monolith Application
- Explainable Link Prediction for Privacy-Preserving Contact Tracing