PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers

Autor:	Amizadeh, Saeed, Matusevych, Sergiy, Weimer, Markus
Rok vydání:	2019
Předmět:	Computer Science - Machine Learning Computer Science - Logic in Computer Science Computer Science - Neural and Evolutionary Computing Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Neuro-symbolic Methods, Neural Combinatorial Optimization, Geometric Deep Learning
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1903.01969 Zobrazit plný text záznamu View this record from Arxiv