CanHybridGeometricScatteringNetworksHelp SolvetheMaximumCliqueProblem?
–Neural Information Processing Systems
Our empirical results demonstrate that our method outperforms representative GNN baselines in terms of solution accuracy and inference speed as well asconventional solverslikeGurobi with limited time budgets.
Neural Information Processing Systems
Feb-10-2026, 17:59:38 GMT
- Country:
- North America
- Canada > Quebec
- Montreal (0.04)
- United States > New York
- Tompkins County > Ithaca (0.04)
- Canada > Quebec
- North America
- Genre:
- Research Report > New Finding (0.48)
- Technology: