A Max-Cut-specific graph neural network predicts primal- and dual-feasible SDP solutions in linearithmic time, cutting bounding costs in exact branch-and-bound by up to 10.6 times versus a commercial SDP solver while training without any solved SDP labels.
At- tending to graph transformers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Standard GNNs fail to recover linear SDP solutions, but a more expressive architecture emulates first-order solvers, achieves lower error on benchmarks, and yields up to 80% speedups when warm-starting solvers.
citing papers explorer
-
Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks
A Max-Cut-specific graph neural network predicts primal- and dual-feasible SDP solutions in linearithmic time, cutting bounding costs in exact branch-and-bound by up to 10.6 times versus a commercial SDP solver while training without any solved SDP labels.
-
On the Expressive Power of GNNs to Solve Linear SDPs
Standard GNNs fail to recover linear SDP solutions, but a more expressive architecture emulates first-order solvers, achieves lower error on benchmarks, and yields up to 80% speedups when warm-starting solvers.