arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.07162cs.LGcs.AI
收藏

目标感知神经SAT求解器

Goal-Aware Neural SAT Solver

Institute of Mathematics;Computer Science University of Latvia

Emils Ozolins, Karlis Freivalds, Andis Draguns, Eliza Gaile, Ronalds Zakovskis, Sergejs Kozlovics

摘要:

现代神经网络获取有关问题的信息,并仅根据输入值计算输出。我们认为,它并不总是最优的,网络的性能可以显着提高,通过增加一个查询机制,允许网络在运行时间,使几个解决方案的试验,并得到反馈的损失值在每次试验。为了证明查询机制的能力,我们制定了一个无监督的(不依赖于标签)损失函数的布尔可满足性问题(SAT),并从理论上表明,它允许网络提取丰富的信息的问题。然后,我们提出了一个神经SAT求解器与查询机制称为QuerySAT,并表明它优于广泛的SAT任务的神经基线。

英文摘要:

Modern neural networks obtain information about the problem and calculate the output solely from the input values. We argue that it is not always optimal, and the network's performance can be significantly improved by augmenting it with a query mechanism that allows the network at run time to make several solution trials and get feedback on the loss value on each trial. To demonstrate the capabilities of the query mechanism, we formulate an unsupervised (not depending on labels) loss function for Boolean Satisfiability Problem (SAT) and theoretically show that it allows the network to extract rich information about the problem. We then propose a neural SAT solver with a query mechanism called QuerySAT and show that it outperforms the neural baseline on a wide range of SAT tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑