arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.01969cs.LGcs.LOcs.NEstat.ML
收藏

PDP:一个学习约束满足求解器的通用神经框架

PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers

Microsoft(微软)

Saeed Amizadeh, Sergiy Matusevych, Markus Weimer

摘要:

最近,人们努力将图神经网络模型用于学习约束满足问题(CSP),特别是布尔可满足性(SAT)的全栈求解器。尽管这些神经嵌入模型具有独特的代表性,但尚不清楚学习模型中的搜索策略实际上是如何工作的。另一方面,通过固定搜索策略(例如贪婪搜索),我们将有效地剥夺神经模型学习比给定策略更好的策略。在本文中,我们提出了一个通用的神经框架学习CSP求解器,可以描述的概率推理,但学习搜索策略超越贪婪搜索。我们的框架基于图形模型中的传播,抽取和预测(因此命名为PDP)的思想,并且可以通过能量最小化以完全无监督的方式直接训练解决CSP,如本文所示。我们的实验结果证明了我们的SAT解决框架的有效性相比,神经和国家的最先进的基线。

英文摘要:

There have been recent efforts for incorporating Graph Neural Network models for learning full-stack solvers for constraint satisfaction problems (CSP) and particularly Boolean satisfiability (SAT). Despite the unique representational power of these neural embedding models, it is not clear how the search strategy in the learned models actually works. On the other hand, by fixing the search strategy (e.g. greedy search), we would effectively deprive the neural models of learning better strategies than those given. In this paper, we propose a generic neural framework for learning CSP solvers that can be described in terms of probabilistic inference and yet learn search strategies beyond greedy search. Our framework is based on the idea of propagation, decimation and prediction (and hence the name PDP) in graphical models, and can be trained directly toward solving CSP in a fully unsupervised manner via energy minimization, as shown in the paper. Our experimental results demonstrate the effectiveness of our framework for SAT solving compared to both neural and the state-of-the-art baselines.

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。

↑