A benchmark built from 50,000 ChEMBL molecules shows that current explainers for graph neural networks often fail to identify the chemical substructures that define the prediction.
Grease: Generate factual and counterfactual explanations for gnn-based recommendations, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
A benchmark built from 50,000 ChEMBL molecules shows that current explainers for graph neural networks often fail to identify the chemical substructures that define the prediction.