Reimagining GNN Explanations with ideas from Tabular Data
arXiv:2106.12665
Abstract
Explainability techniques for Graph Neural Networks still have a long way to go compared to explanations available for both neural and decision decision tree-based models trained on tabular data. Using a task that straddles both graphs and tabular data, namely Entity Matching, we comment on key aspects of explainability that are missing in GNN model explanations.
arXiv comment4 pages, 8 figures, XAI Workshop at ICML 2021
References in corpus (5)
- On Explainability of Graph Neural Networks via Subgraph Explorations
- Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
- Link Prediction using Graph Neural Networks for Master Data Management
- Explainable Link Prediction for Privacy-Preserving Contact Tracing
- Towards Automated Evaluation of Explanations in Graph Neural Networks