HGODE adds a learnable double-well edge potential and bipolar gate to Graph ODEs so topology can polarize into connected or disconnected phases without losing differentiability or falling into global consensus.
arXiv preprint arXiv:2411.07672 , year=
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
TAGR repairs graphs with sparse Gaussian feature-neighborhood edges plus topology-aware residual correction to boost GNN robustness on noisy or incomplete citation networks.
citing papers explorer
-
Latent-Hysteresis Graph ODEs: Modeling Coupled Topology-Feature Evolution via Continuous Phase Transitions
HGODE adds a learnable double-well edge potential and bipolar gate to Graph ODEs so topology can polarize into connected or disconnected phases without losing differentiability or falling into global consensus.
-
Topology-Aware Gaussian Graph Repair for Robust Graph Neural Networks
TAGR repairs graphs with sparse Gaussian feature-neighborhood edges plus topology-aware residual correction to boost GNN robustness on noisy or incomplete citation networks.