论文标题
谨慎增强：组合问题的对比度学习
Augment with Care: Contrastive Learning for Combinatorial Problems
论文作者
论文摘要
监督学习可以改善最先进的求解器的组合问题的设计，但是由于指数性的最差复杂性，标记大量组合实例通常是不切实际的。受图像的对比预训练的最新成功的启发，我们对增强设计对布尔满意度问题的对比预训练的影响进行了科学研究。虽然典型的图形对比前训练使用了标签 - 敏捷的增强，但我们的主要见解是，许多组合问题都有良好的态度，这允许设计具有标签的增强功能。我们发现，具有标签的增强对于对比前训练的成功至关重要。我们表明，我们的表示形式能够达到仅使用1％标签的完全监督学习的可比测试准确性。我们还证明，我们的表示形式更容易转移到看不见的域中的更大问题。我们的代码可在https://github.com/h4duan/contrastive-sat上找到。
Supervised learning can improve the design of state-of-the-art solvers for combinatorial problems, but labelling large numbers of combinatorial instances is often impractical due to exponential worst-case complexity. Inspired by the recent success of contrastive pre-training for images, we conduct a scientific study of the effect of augmentation design on contrastive pre-training for the Boolean satisfiability problem. While typical graph contrastive pre-training uses label-agnostic augmentations, our key insight is that many combinatorial problems have well-studied invariances, which allow for the design of label-preserving augmentations. We find that label-preserving augmentations are critical for the success of contrastive pre-training. We show that our representations are able to achieve comparable test accuracy to fully-supervised learning while using only 1% of the labels. We also demonstrate that our representations are more transferable to larger problems from unseen domains. Our code is available at https://github.com/h4duan/contrastive-sat.
