A GNN framework that simulates primal-dual approximation algorithms for NP-hard problems and, with small-instance optimal labels, can beat the algorithm it learns.
Title resolution pending
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
-
Primal-Dual Neural Algorithmic Reasoning
A GNN framework that simulates primal-dual approximation algorithms for NP-hard problems and, with small-instance optimal labels, can beat the algorithm it learns.