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.
Neural network-based dimensionality reduction for large-scale binary optimization with millions of variables
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 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.