Local d-hop uniqueness in GNN node features matches global UID expressiveness for ILP solving while providing stronger generalization.
On representing linear pro- grams by graph neural networks.arXiv preprint arXiv:2209.12288,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices
Local d-hop uniqueness in GNN node features matches global UID expressiveness for ILP solving while providing stronger generalization.