CIExplainer uses causal inference via the Potential Outcome Framework to find high-impact subgraphs for GNN explanations, with G2TeXplainer generating feature and relation-aware natural language descriptions.
Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks
CIExplainer uses causal inference via the Potential Outcome Framework to find high-impact subgraphs for GNN explanations, with G2TeXplainer generating feature and relation-aware natural language descriptions.