A triangle-message GNN for multicut outperforms heuristics in solution quality on graphs up to 200 nodes and finds optimal solutions faster than exact solvers for some cases.
Learning to Compare Nodes in Branch and Bound with Graph Neural Networks , booktitle =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Graph Neural Networks with Triangle-Based Messages for the Multicut Problem
A triangle-message GNN for multicut outperforms heuristics in solution quality on graphs up to 200 nodes and finds optimal solutions faster than exact solvers for some cases.