Research map / Graph learning / GNN architectures
SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations
Ziyuan Ye, Rihan Huang, Qilin Wu, Quanying Liu
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 |
|---|---|---|---|
| SAME vs previous SOTA explainer | SAME · BBBP | fidelity: 0.433 -> 0.489 | Improved |
| SAME vs previous SOTA explainer | SAME · MUTAG | fidelity: 0.656 -> 0.702 | Improved |
| SAME vs previous SOTA explainer | SAME · Graph-SST2 | fidelity: 0.262 -> 0.373 | Improved |
| SAME vs previous SOTA explainer | SAME · Graph-SST5 | fidelity: 0.283 -> 0.393 | Improved |
| SAME vs previous SOTA explainer | SAME · BA-2Motifs | fidelity: 0.493 -> 0.549 | Improved |
| SAME vs previous SOTA explainer | SAME · BA-Shapes | fidelity: 0.181 -> 0.214 | Improved |
| SAME vs previous SOTA on harmonic fidelity | SAME · graph classification datasets | harmonic fidelity: 1.92% | Improved |
| SAME vs SOTA on inverse fidelity | SAME · 6 datasets | inverse fidelity | Mixed |
| SAME vs SubgraphX on cost | SAME · BBBP | inference time (s): 26.72 -> 7.86 | Improved |
| SAME vs GStarX on cost | SAME · BBBP | inference time (s): 84.54 -> 7.86 | Improved |
| Increase K from 1 to 9 at gamma=1 (ablation) | SAME · Graph-SST5 (30 graphs) | fidelity: 0.2511 -> 0.4026 | Improved |
| Increase gamma from 1 to 5 at K=7 (ablation) | SAME · Graph-SST5 (30 graphs) | fidelity: 0.3938 -> 0.3591 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GStarX — GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games (NeurIPS 2022) · better on 12 of 12 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective (ICML 2025 · similarity 0.91)
- 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)
- Explaining Graph Neural Networks via Structure-aware Interaction Index (ICML 2024 · similarity 0.90)
- EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time (ICML 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.
