Research map / Graph learning / GNN architectures
Reinforcement Learning Enhanced Explainer for Graph Neural Networks
Caihua Shan, Yifei Shen, Yao Zhang, Xiang Li, Dongsheng Li
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 |
|---|---|---|---|
| replace continuous edge-mask explainers with RL sequential connected-subgraph generation | RG-Explainer vs PGExplainer · Tree-Grid | explanation AUC: 0.714 -> 0.927 | Improved |
| RG-Explainer vs PGExplainer | RG-Explainer · BA-Shapes | explanation AUC: 0.999 -> 0.985 | Hurt |
| RG-Explainer vs PGExplainer | RG-Explainer · BA-2motifs | explanation AUC: 0.133 -> 0.657 | Improved |
| RG-Explainer vs PGExplainer | RG-Explainer · BA-Community | explanation AUC: 0.825 -> 0.919 | Improved |
| RG-Explainer vs PGExplainer | RG-Explainer · Tree-Cycles | explanation AUC: 0.760 -> 0.787 | Improved |
| RG-Explainer vs PGExplainer | RG-Explainer · MUTAG | explanation AUC: 0.847 -> 0.873 | Improved |
| RG-Explainer vs PGExplainer with small training set (10%) in inductive setting | RG-Explainer · Tree-Grid inductive | explanation AUC | Improved |
Closest papers by meaning
- EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time (ICML 2024 · similarity 0.91)
- Stratified GNN Explanations through Sufficient Expansion (AAAI 2024 · similarity 0.90)
- Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks (ICML 2024 · similarity 0.90)
- GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules (NeurIPS 2024 · similarity 0.90)
- Graph Segmentation and Contrastive Enhanced Explainer for Graph Neural Networks (AAAI 2025 · similarity 0.90)
- Self-Interpretable Graph Learning with Sufficient and Necessary Explanations (AAAI 2024 · similarity 0.89)
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.
