Estimating cardinalities with deep sketches
Kipf A, Vorona D, Mueller J, Kipf T, Radke B, Leis V, Boncz P, Neumann T, Kemper A (2019)
Publication Type: Conference contribution
Publication year: 2019
Publisher: Association for Computing Machinery
Pages Range: 1937-1940
Conference Proceedings Title: Proceedings of the ACM SIGMOD International Conference on Management of Data
Event location: Amsterdam
ISBN: 9781450356435
Abstract
We introduce Deep Sketches, which are compact models of databases that allow us to estimate the result sizes of SQL queries. Deep Sketches are powered by a new deep learning approach to cardinality estimation that can capture correlations between columns, even across tables. Our demonstration allows users to define such sketches on the TPC-H and IMDb datasets, monitor the training process, and run ad-hoc queries against trained sketches. We also estimate query cardinalities with HyPer and PostgreSQL to visualize the gains over traditional cardinality estimators.
Authors with CRIS profile
Involved external institutions
University of Amsterdam
Netherlands (NL)
Centrum Wiskunde & Informatica (CWI)
Netherlands (NL)
Technische Universität München (TUM)
Germany (DE)
Netherlands (NL)
Centrum Wiskunde & Informatica (CWI)
Netherlands (NL)
Technische Universität München (TUM)
Germany (DE)
How to cite
APA:
Kipf, A., Vorona, D., Mueller, J., Kipf, T., Radke, B., Leis, V.,... Kemper, A. (2019). Estimating cardinalities with deep sketches. In Proceedings of the ACM SIGMOD International Conference on Management of Data (pp. 1937-1940). Amsterdam, NL: Association for Computing Machinery.
MLA:
Kipf, Andreas, et al. "Estimating cardinalities with deep sketches." Proceedings of the 2019 International Conference on Management of Data, SIGMOD 2019, Amsterdam Association for Computing Machinery, 2019. 1937-1940.
BibTeX: Download