SpecGap adjusts GNN features by subtracting the second-largest Laplacian eigenvector component times the spectral gap, claiming improved graph OOD detection without retraining.
Expander graphs and their applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps
SpecGap adjusts GNN features by subtracting the second-largest Laplacian eigenvector component times the spectral gap, claiming improved graph OOD detection without retraining.