Gauss: program synthesis by reasoning over graphs

Gauss: program synthesis by reasoning over graphs
复制标题

高斯:通过图推理进行程序综合

DOI:
10.1145/3485511
复制
发表时间:
2021
影响因子:
--
通讯作者:
Stoica, Ion
Stoica, Ion
中科院分区:
--
文献类型:
--
作者:
Bavishi, Rohan;Lemieux, Caroline;Sen, Koushik;Stoica, Ion

文献摘要

参考文献

被引文献

相似文献

虽然输入输出示例是程序合成引擎的一种自然形式的规范,但对于表转换等领域来说,它们可能不精确。在本文中,我们将研究如何提取这些输入输出示例背后的用户意图的现成信息,以帮助加速合成并减少过拟合。我们提出了高斯,表转换,接受部分输入输出的例子,沿着与用户意图图的合成算法。Gauss包含了一种新的基于图的冲突解决推理算法,使其能够从搜索过程中的错误中学习,并利用这些知识更快地探索程序空间。它还确保最终程序与用户意图规范一致,减少过拟合。我们为表转换域实现了高斯(支持Pandas和R),并将其与三种仅接受输入输出示例的最先进的合成器进行了比较。我们发现,它能够减少搜索空间的56倍,73倍和664倍的平均,导致7倍,26倍和7倍的加速合成时间,分别平均。
While input-output examples are a natural form of specification for program synthesis engines, they can be imprecise for domains such as table transformations. In this paper, we investigate how extracting readily-available information about the user intent behind these input-output examples helps speed up synthesis and reduce overfitting. We present Gauss, a synthesis algorithm for table transformations that accepts partial input-output examples, along with user intent graphs. Gauss includes a novel conflict-resolution reasoning algorithm over graphs that enables it to learn from mistakes made during the search and use that knowledge to explore the space of programs even faster. It also ensures the final program is consistent with the user intent specification, reducing overfitting. We implement Gauss for the domain of table transformations (supporting Pandas and R), and compare it to three state-of-the-art synthesizers accepting only input-output examples. We find that it is able to reduce the search space by 56×, 73× and 664× on average, resulting in 7×, 26× and 7× speedups in synthesis times on average, respectively.
通过交互式草图综合查询
DOI: --
发表时间: 2019
期刊: arXiv.org
影响因子: --
作者:
O. Bastani;Xin Zhang;Armando Solar
通讯作者: Armando Solar
按谓词编程:交互式综合的形式模型
DOI: --
发表时间: 2019
期刊: Acta Informatica
影响因子: 0.6
作者:
Hila Peleg;Shachar Itzhaky;Sharon Shoham;Eran Yahav
通讯作者: Eran Yahav
DOI: 10.1145/3158151
发表时间: 2017-10
影响因子: --
作者:
Xinyu Wang;Işıl Dillig;Rishabh Singh
通讯作者: Xinyu Wang;Işıl Dillig;Rishabh Singh
DOI: 10.1145/3296979.3192382
发表时间: 2017-11
影响因子: --
作者:
Yu Feng;R. Martins;O. Bastani;Işıl Dillig
通讯作者: Yu Feng;R. Martins;O. Bastani;Işıl Dillig
数据整理的原理 数据准备的实用技术
DOI: --
发表时间: 2017
期刊:
影响因子: --
作者:
J. Hellerstein;Jeffrey Heer;Sean Kandel;Connor Carreras
通讯作者: Connor Carreras