An unsupervised GNN solver using one-hot polynomial objectives is fast on large graphs but does not consistently beat SCIP, KaHyPar, or hMETIS on solution quality.
Controlling continuous relaxation for combinatorial optimization.Advances in Neural Information Processing Systems (NeurIPS), 37:47189–47216, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Deep k-grouping: An Unsupervised Learning Framework for Combinatorial Optimization on Graphs and Hypergraphs
An unsupervised GNN solver using one-hot polynomial objectives is fast on large graphs but does not consistently beat SCIP, KaHyPar, or hMETIS on solution quality.