Estimating Filtered Group-By Queries is Hard : Deep Learning to the Rescue

Estimating Filtered Group-By Queries is Hard : Deep Learning to the Rescue
复制标题

估计过滤后的分组查询很困难:深度学习来救援

DOI:
--
复制
发表时间:
2019
期刊:
影响因子:
--
通讯作者:
M. Freitag
M. Freitag
中科院分区:
--
文献类型:
--
作者:
Andreas Kipf;M. Freitag

文献摘要

参考文献

被引文献

相似文献

虽然估计基表上group-by操作的结果大小本身就很困难,但选择的存在使这个问题越来越难以解决。我们表明,在真实数据中发现的倾斜数据分布和相关性严重影响传统基数估计器的结果。另一方面,深度学习最近被证明是一种更健壮的基数估计方法。我们的评估表明,我们的(基于集合的)深度学习模型显着提高了基数估计过滤组的质量。
While estimating the result size of a group-by operation on a base table is hard on its own, the presence of selections makes this problem increasingly difficult to solve. We show that skewed data distributions and correlations found in real-world data heavily affect the results of traditional cardinality estimators. On the other hand, deep learning has recently been shown to be a more robust approach to cardinality estimation. Our evaluation shows that our (setbased) deep learning model significantly enhances the quality of filtered group-by cardinality estimates.
DOI: 10.1109/icde.2011.5767867
发表时间: 2011
期刊: 2011 IEEE 27th International Conference on Data Engineering
影响因子: --
作者:
A. Kemper;T. Neumann
通讯作者: T. Neumann