This website is under development. If you come accross any issues, please report them to Konstantinos Kanellis
(kkanellis@cs.wisc.edu) or Yannis Chronis
(chronis@google.com).
Learned Cardinalities: Estimating Correlated Joins with Deep Learning
Abstract
We describe a new deep learning approach to cardinality estimation. MSCN is a multi-set convolutional network, tailored to representing relational query plans, that employs set semantics to capture query features and true cardinalities. MSCN builds on sampling-based estimation, addressing its weaknesses when no sampled tuples qualify a predicate, and in capturing join-crossing correlations. Our evaluation of MSCN using a real-world dataset shows that deep learning signiicantly enhances the quality of cardinality estimation, which is the core problem in query optimization.
Citation
@inproceedings{cidr/2019/101-kipf-cidr19,
author = {Andreas Kipf and
Thomas Kipf and
Bernhard Radke and
Viktor Leis and
Peter Boncz and
Alfons Kemper},
title = {Learned Cardinalities: Estimating Correlated Joins with Deep Learning},
booktitle = {Proceedings of the 9th Conference on Innovative Data Systems Research, CIDR 2019},
publisher = {www.cidrdb.org},
year = {2019},
series = {CIDR 2019},
url = {https://cidr.org/temp-website/papers/2019/p101-kipf-cidr19.pdf},
location = {Asilomar, CA, USA}
}