Papers › SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations
SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations
Post-hoc explanation techniques on graph neural networks (GNNs) provide economical solutions for opening the black-box graph models without model retraining. Many GNN explanation variants have achieved state-of-the-art explaining results on a diverse set of benchmarks, while they rarely provide theoretical analysis for their inherent properties and explanatory capability. In this work, we propose Structure-Aware Shapley-based Multipiece Explanation (SAME) method to address the structure-aware feature interactions challenges for GNNs explanation. Specifically, SAME leverages an expansion-based Monte Carlo tree search to explore the multi-grained structure-aware connected substructure. Afterward, the explanation results are encouraged to be informative of the graph properties by optimizing the combination of distinct single substructures. With the consideration of fair feature interactions in the process of investigating multiple connected important substructures, the explanation provided by SAME has the potential to be as explainable as the theoretically optimal explanation obtained by the Shapley value within polynomial time. Extensive experiments on real-world and synthetic benchmarks show that SAME improves the previous state-of-the-art fidelity performance by 12.9\% on BBBP, 7.01\% on MUTAG, 42.3\% on Graph-SST2, 38.9\% on Graph-SST5, 11.3\% on BA-2Motifs and 18.2\% on BA-Shapes under the same testing condition. Code is available at https://github.com/same2023neurips/same.Submission Number: 12143
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Explanation Fidelity Evaluation | BA-2motifs | GCN | fidelity | 0.549 | #1 of 1 | Archive leaderboard | report |
| Explanation Fidelity Evaluation | BA-Shapes | GCN | fidelity | 0.214 | #1 of 1 | Archive leaderboard | report |
| Explanation Fidelity Evaluation | BBBP | GCN | fidelity | 0.489 | #1 of 1 | Archive leaderboard | report |
| Explanation Fidelity Evaluation | MUTAG | GCN | fidelity | 0.702 | #1 of 1 | Archive leaderboard | report |
| Explanation Fidelity Evaluation | SST-5 | GCN | fidelity | 0.393 | #1 of 1 | Archive leaderboard | report |
| Explanation Fidelity Evaluation | SST2 | GCN | fidelity | 0.373 | #1 of 1 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections