Research map / Graph learning / GNN architectures
PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks
Yong-Min Shin, Sunwoo Kim, Won-Yong Shin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 PAGE instead of XGNN | GCN explanations · BA-house | accuracy: 0.2500 -> 0.5238 | Improved |
| use PAGE instead of XGNN | GCN explanations · BA-grid | accuracy: 0.3200 -> 0.8571 | Improved |
| use PAGE instead of XGNN | GCN explanations · MUTAG | accuracy: 0.6875 -> 0.9090 | Improved |
| use PAGE instead of XGNN | GCN explanations · Benzene | accuracy: 0.2500 -> 0.6667 | Improved |
| use PAGE instead of XGNN | GCN explanations · Solubility | density: 0.1195 -> 0.0462 | Improved |
| use PAGE instead of XGNN | GCN explanations · BA-house | density: 0.1235 -> 0.1481 | Hurt |
| use PAGE instead of XGNN | GCN explanations · BA-house | consistency: 0.2152 -> 0.0308 | Improved |
| use PAGE instead of XGNN | GCN explanations · MUTAG | consistency: 0.1269 -> 0.1216 | No clear effect |
| use PAGE instead of XGNN | GCN explanations · MNIST-sp | consistency: 0.0242 -> 0.1025 | Hurt |
| use PAGE instead of XGNN | GCN explanations · BA-house | faithfulness: -0.4037 -> 0.7340 | Improved |
| use PAGE instead of XGNN | GCN explanations · MNIST-sp | faithfulness: 0.1273 -> 0.8182 | Improved |
| use PAGE instead of XGNN | GCN explanations · MUTAG | faithfulness: 0.2504 -> 0.4430 | Improved |
Closest papers by meaning
- Self-Interpretable Graph Learning with Sufficient and Necessary Explanations (AAAI 2024 · similarity 0.91)
- Stratified GNN Explanations through Sufficient Expansion (AAAI 2024 · similarity 0.90)
- EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time (ICML 2024 · similarity 0.90)
- Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective (ICML 2025 · 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)
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.
