Graph Neural Networks vs Convolutional Neural Networks for Graph Domination Number Prediction
By: Randy Davila, Beyzanur Ispir
Potential Business Impact:
Helps computers find the smallest group to control a network.
We investigate machine learning approaches to approximating the \emph{domination number} of graphs, the minimum size of a dominating set. Exact computation of this parameter is NP-hard, restricting classical methods to small instances. We compare two neural paradigms: Convolutional Neural Networks (CNNs), which operate on adjacency matrix representations, and Graph Neural Networks (GNNs), which learn directly from graph structure through message passing. Across 2,000 random graphs with up to 64 vertices, GNNs achieve markedly higher accuracy ($R^2=0.987$, MAE $=0.372$) than CNNs ($R^2=0.955$, MAE $=0.500$). Both models offer substantial speedups over exact solvers, with GNNs delivering more than $200\times$ acceleration while retaining near-perfect fidelity. Our results position GNNs as a practical surrogate for combinatorial graph invariants, with implications for scalable graph optimization and mathematical discovery.
Similar Papers
A Distributed Training Architecture For Combinatorial Optimization
Machine Learning (CS)
Solves hard problems on huge networks faster.
Statistical physics analysis of graph neural networks: Approaching optimality in the contextual stochastic block model
Disordered Systems and Neural Networks
Makes computers understand complex connections better.
Community detection robustness of graph neural networks
Social and Information Networks
Makes computer groups find real connections better.