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.
Journal of Complex Networks , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it