ALECE: An Attention-based Learned Cardinality Estimator for SPJ Queries on Dynamic Workloads
Proceedings of the VLDB Endowment · 2023-10 · 17 (2) · 197-210
DOI: 10.14778/3626292.3626302 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, 2023-10. Verfasst von Pengfei Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 67 Literaturangaben.
Abstract (Originalsprache)
For efficient query processing, DBMS query optimizers have for decades relied on delicate cardinality estimation methods. In this work, we propose an Attention-based LEarned Cardinality Estimator ( ALECE for short) for SPJ queries. The core idea is to discover the implicit relationships between queries and underlying dynamic data using attention mechanisms in ALECE's two modules that are built on top of carefully designed featurizations for data and queries. In particular, from all attributes in the database, the data-encoder module obtains organic and learnable aggregations which implicitly represent correlations among the attributes, whereas the query-analyzer module builds a bridge between the query featurizations and the data aggregations to predict the query's cardinality. We experimentally evaluate ALECE on multiple dynamic workloads. The results show that ALECE enables PostgreSQL's optimizer to achieve nearly optimal performance, clearly outperforming its built-in cardinality estimator and other alternatives.
Zitieren
APA
Li, P., Wei, W., Zhu, R., Ding, B., Zhou, J., & Lu, H. (2023). ALECE: An Attention-based Learned Cardinality Estimator for SPJ Queries on Dynamic Workloads. Proceedings of the VLDB Endowment, 17(2), 197-210. https://doi.org/10.14778/3626292.3626302
Vancouver
Li P, Wei W, Zhu R, Ding B, Zhou J, Lu H. ALECE: An Attention-based Learned Cardinality Estimator for SPJ Queries on Dynamic Workloads. Proceedings of the VLDB Endowment. 2023;17(2):197-210. doi:10.14778/3626292.3626302
BibTeX
@article{Li2023,
author = {Li, Pengfei and Wei, Wenqing and Zhu, Rong and Ding, Bolin and Zhou, Jingren and Lu, Hua},
title = {ALECE: An Attention-based Learned Cardinality Estimator for SPJ Queries on Dynamic Workloads},
journal = {Proceedings of the VLDB Endowment},
year = {2023},
volume = {17},
number = {2},
pages = {197--210},
doi = {10.14778/3626292.3626302}
}
EUVIMED