← Search

Minghui Ouyang

2 accepted papers

2025

Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming

ICLR 2025poster

Graph neural networks (GNNs) have recently emerged as powerful tools for solving complex optimization problems, often being employed to approximate solution mappings. Empirical evidence shows that even shallow GNNs (with fewer than ten layers) can achieve strong performance in predicting optimal sol…

Cited by 0SourcePDFScholar
2024

On the Power of Small-size Graph Neural Networks for Linear Programming

NeurIPS 2024poster

Graph neural networks (GNNs) have recently emerged as powerful tools for addressing complex optimization problems. It has been theoretically demonstrated that GNNs can universally approximate the solution mapping functions of linear programming (LP) problems. However, these theoretical results typic…

Cited by 0SourcePDFScholar