关于图组合优化预训练的有效性
On the Effectiveness of Pretraining for Graph Combinatorial Optimization
浏览论文内容
中文总结 AI 辅助
研究图组合优化的预训练有效性，提出自监督预训练框架，利用图对比学习和几何增强，使模型学习不变表示与距离分布，实验表明该策略优于未预训练模型，混合策略在TSP1000上有显著提升。
中文摘要 AI 辅助
本文介绍了一种用于图组合优化的自监督预训练框架，专门针对旅行商问题等路由问题的性质设计。通过利用带有几何增强（具体为旋转和轴向反射）的图对比学习，迫使模型学习不变的结构表示和全局相对距离分布。结果表明，该预训练策略在各种问题规模上均优于未预训练的模型。特别是，混合策略（结合旋转和反射）在TSP1000的巡回长度上提高了6.57%，证明几何预训练是将神经求解器有效扩展到高维实例的重要归纳偏差。
英文摘要
This paper introduces a self-supervised pretraining framework for graph combinatorial optimization specifically designed to address the nature of routing problems like the Traveling Salesman Problem. By utilizing graph contrastive learning with geometric augmentations (specifically, rotations and axial reflections) the model is forced to learn invariant structural representations and global relative distance distributions. Results demonstrate that this pretraining strategy outperforms non-pretrained models across various problem scales. Notably, the hybrid strategy (combining rotation and reflection) achieved a 6.57% improvement in tour length for TSP1000, proving that geometric pretraining is an important inductive bias for effectively scaling neural solvers to high-dimensional instances.
