Learning Symmetric Rules with SATNet

arXiv2206.13998MaRDI QIDQ6403392FDOQ6403392

Authors: Sangho Lim, Eun-Gyeol Oh, Hongseok Yang 

Publication date: 28 June 2022

Abstract: SATNet is a differentiable constraint solver with a custom backpropagation algorithm, which can be used as a layer in a deep-learning system. It is a promising proposal for bridging deep learning and logical reasoning. In fact, SATNet has been successfully applied to learn, among others, the rules of a complex logical puzzle, such as Sudoku, just from input and output pairs where inputs are given as images. In this paper, we show how to improve the learning of SATNet by exploiting symmetries in the target rules of a given but unknown logical puzzle or more generally a logical formula. We present SymSATNet, a variant of SATNet that translates the given symmetries of the target rules to a condition on the parameters of SATNet and requires that the parameters should have a particular parametric form that guarantees the condition. The requirement dramatically reduces the number of parameters to learn for the rules with enough symmetries, and makes the parameter learning of SymSATNet much easier than that of SATNet. We also describe a technique for automatically discovering symmetries of the target rules from examples. Our experiments with Sudoku and Rubik's cube show the substantial improvement of SymSATNet over the baseline SATNet.

Has companion code repository: https://github.com/Lim-Sangho/SymSATNet

This page was built for publication: Learning Symmetric Rules with SATNet

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6403392)