Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-1044
Counterfactual GNN explainers produce statistically infeasible recourses that violate topological constraints in molecular datasets
IC-1045
Factual GNN explanations do not capture the full data signal: retraining on explanations fails to reproduce predictions while retraining on residuals preserves them