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
中科院分区:
文献类型:
--
作者:
Bavishi, Rohan;Lemieux, Caroline;Sen, Koushik;Stoica, Ion
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.
登录
查看更多内容
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
影响因子:
0.6
作者:
Hila Peleg;Shachar Itzhaky;Sharon Shoham;Eran Yahav
通讯作者:
Eran Yahav
影响因子:
--
作者:
Xinyu Wang;Işıl Dillig;Rishabh Singh
通讯作者:
Xinyu Wang;Işıl Dillig;Rishabh Singh
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
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