GIST generates graph counterfactuals by overshooting to another class and backtracking with a spectral style loss, reporting higher validity and fidelity on 8 graph classification datasets.
Coun- tergan: Generating counterfactuals for real-time recourse and interpretability using residual gans
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Graph Inverse Style Transfer for Counterfactual Explainability
GIST generates graph counterfactuals by overshooting to another class and backtracking with a spectral style loss, reporting higher validity and fidelity on 8 graph classification datasets.