A completion-aware framework for counterfactual explainability in GNNs that integrates factual explanations with missing edge prediction to improve explanation quality, robustness, and intuitiveness.
IEEE Trans
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.
citing papers explorer
-
A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networks
A completion-aware framework for counterfactual explainability in GNNs that integrates factual explanations with missing edge prediction to improve explanation quality, robustness, and intuitiveness.
-
Explaining Graph Neural Networks for Node Similarity on Graphs
Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.