.png){kind=icon}
.png){kind=icon}
Return
Graph Convolutional Branch and Bound
.png){kind=icon}
OA
AI
DOI：10.1016/j.ejor.2026.03.036.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• New unsupervised training pipeline for graph neural networks • Neural scores guide branch-and-bound in variable and node selection • Tests on TSPLIB and random instances with different sizes and geometries • Fewer branch and bound nodes explored and shallower trees • Hybrid method solves TSP instances faster than traditional solvers like Concorde
Keywords:
Traveling salesman
Combinatorial optimization
Branch and bound
Graph neural network
Deep learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6
Papers:
2.2W
Citations:
6.4W
Organization
No organization information available