Orbit-based feature augmentation, which assigns distinct random values within each orbit of an ILP's symmetry group, lets GNNs distinguish symmetric variables and improves solution-prediction accuracy on bin packing, balanced item placement, and steel mill slab problems.
The machine learning for combinatorial optimization competition (ml4co): Results and insights
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach
Orbit-based feature augmentation, which assigns distinct random values within each orbit of an ILP's symmetry group, lets GNNs distinguish symmetric variables and improves solution-prediction accuracy on bin packing, balanced item placement, and steel mill slab problems.