An EFGN learns directed improvement graphs over combinatorial spaces to act as a recommender for MCNLP solvers, yielding better optima than index-based baselines when paired with PSO and GA on benchmarks.
Pattern databases,
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
-
Learning-based Directed Graph Abstraction of Combinatorial Spaces for Order-Preserving Search in Mixed-Combinatorial Nonlinear Optimization
An EFGN learns directed improvement graphs over combinatorial spaces to act as a recommender for MCNLP solvers, yielding better optima than index-based baselines when paired with PSO and GA on benchmarks.