HH-MPNN achieves under 1% optimality gap on default topologies from 14 to 2000 buses, zero-shot N-1 generalization under 3% gap, and improved size generalization via pre-training on small grids.
From Local Structures to Size Generalization in Graph Neural Networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A probabilistic graphical model framework with graph neural network inference computes Bayesian posteriors for discrete structural states, claimed to match traditional Bayesian results while scaling to high-dimensional problems via topology-informed learning and scale-adaptive training.
citing papers explorer
-
Towards Generalization of Graph Neural Networks for AC Optimal Power Flow
HH-MPNN achieves under 1% optimality gap on default topologies from 14 to 2000 buses, zero-shot N-1 generalization under 3% gap, and improved size generalization via pre-training on small grids.
-
Probabilistic Graphical Model using Graph Neural Networks for Bayesian Inversion of Discrete Structural Component States
A probabilistic graphical model framework with graph neural network inference computes Bayesian posteriors for discrete structural states, claimed to match traditional Bayesian results while scaling to high-dimensional problems via topology-informed learning and scale-adaptive training.