FSpecGNN generalizes spectral GNNs to a second-order form via node-pair lifting and bivariate spectral filters, matching Local 2-GNN expressivity while universally approximating node-pair signals and admitting scalable low-rank implementations.
Journal of Complex Networks , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
QpiGNN provides a quantile-free dual-head architecture for GNN uncertainty quantification that directly optimizes coverage and interval width, yielding 22% higher coverage and 50% narrower intervals than baselines on 19 benchmarks with asymptotic coverage guarantees under mild assumptions.
citing papers explorer
-
Full-Spectrum Graph Neural Networks: Expressive and Scalable
FSpecGNN generalizes spectral GNNs to a second-order form via node-pair lifting and bivariate spectral filters, matching Local 2-GNN expressivity while universally approximating node-pair signals and admitting scalable low-rank implementations.
-
Quantile-Free Uncertainty Quantification in Graph Neural Networks
QpiGNN provides a quantile-free dual-head architecture for GNN uncertainty quantification that directly optimizes coverage and interval width, yielding 22% higher coverage and 50% narrower intervals than baselines on 19 benchmarks with asymptotic coverage guarantees under mild assumptions.