XGNNCert certifies that a GNN explanation keeps at least lambda edges under any graph perturbation of bounded size, using majority voting over hash-partitioned hybrid subgraphs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
XGNNCert certifies that a GNN explanation keeps at least lambda edges under any graph perturbation of bounded size, using majority voting over hash-partitioned hybrid subgraphs.