OPEN clusters training graphs into inferred environments and trains a variational subgraph generator to explain GNN predictions across distribution shifts without model internals or edge weights.
Good: A graph out-of-distribution benchmark
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
unclear 1representative citing papers
citing papers explorer
-
Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks
OPEN clusters training graphs into inferred environments and trains a variational subgraph generator to explain GNN predictions across distribution shifts without model internals or edge weights.