Research map / Graph learning / GNN architectures
PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use PGM-Explainer instead of SHAP | GNN explanations · Syn 1 | accuracy: 0.947 -> 0.965 | Helped |
| Use PGM-Explainer instead of GNNExplainer | GNN explanations · Syn 2 | accuracy: 0.836 -> 0.926 | Helped |
| Use PGM-Explainer instead of GNNExplainer | GNN explanations · Syn 3 | accuracy: 0.741 -> 0.885 | Helped |
| Use PGM-Explainer instead of GNNExplainer | GNN explanations · Syn 4 | accuracy: 0.948 -> 0.954 | Helped |
| Use PGM-Explainer instead of GNNExplainer | GNN explanations · Syn 5 | accuracy: 0.875 -> 0.878 | Helped |
| Use PGM-Explainer instead of SHAP | GNN explanations · Syn 6 | accuracy: 0.741 -> 0.953 | Helped |
| Use PGM-Explainer instead of SHAP | GNN explanations · Bitcoin-alpha top 3 | precision: 0.537 -> 0.873 | Helped |
| Use PGM-Explainer instead of SHAP | GNN explanations · Bitcoin-alpha top 4 | precision: 0.498 -> 0.857 | Helped |
| Use PGM-Explainer instead of SHAP | GNN explanations · Bitcoin-alpha top 5 | precision: 0.465 -> 0.848 | Helped |
| Use PGM-Explainer instead of SHAP | GNN explanations · Bitcoin-OTC top 3 | precision: 0.607 -> 0.833 | Helped |
| Use PGM-Explainer instead of SHAP | GNN explanations · Bitcoin-OTC top 4 | precision: 0.587 -> 0.817 | Helped |
| Use PGM-Explainer instead of SHAP | GNN explanations · Bitcoin-OTC top 5 | precision: 0.566 -> 0.808 | Helped |
Closest papers by meaning
- [Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks (NeurIPS 2024 · similarity 0.90)
- Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks (ICLR 2024 · similarity 0.90)
- GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules (NeurIPS 2024 · similarity 0.90)
- Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks (ICML 2024 · similarity 0.90)
- Factorized Explainer for Graph Neural Networks (AAAI 2024 · similarity 0.90)
- EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time (ICML 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.