Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-30586| Publication type: | Article in scientific journal |
| Type of review: | Peer review (publication) |
| Title: | Is your learned query optimizer behaving as you expect? : a machine learning perspective |
| Authors: | Lehmann, Claude Sulimov, Pavel Stockinger, Kurt |
| et. al: | No |
| DOI: | 10.21256/zhaw-30586 |
| Published in: | Proceedings of the VLDB Endowment |
| Volume(Issue): | 17 |
| Issue: | 7 |
| Page(s): | 1565 |
| Pages to: | 1577 |
| Issue Date: | Mar-2024 |
| Publisher / Ed. Institution: | Association for Computing Machinery |
| ISSN: | 2150-8097 |
| Language: | English |
| Subjects: | Database; Query optimization; Machine learning |
| Subject (DDC): | 006: Special computer methods |
| Abstract: | The current boom of learned query optimizers (LQO) can be explained not only by the general continuous improvement of deep learning (DL) methods but also by the straightforward formulation of a query optimization problem (QOP) as a machine learning (ML) one. The idea is often to replace dynamic programming approaches, widespread for solving QOP, with more powerful methods such as reinforcement learning. However, such a rapid "game change" in the field of QOP could not pass without consequences - other parts of the ML pipeline, except for predictive model development, have large improvement potential. For instance, different LQOs introduce their own restrictions on training data generation from queries, use an arbitrary train/validation approach, and evaluate on a voluntary split of benchmark queries. In this paper, we attempt to standardize the ML pipeline for evaluating LQOs by introducing a new end-to-end benchmarking framework. Additionally, we guide the reader through each data science stage in the ML pipeline and provide novel insights from the machine learning perspective, considering the specifics of QOP. Finally, we perform a rigorous evaluation of existing LQOs, showing that PostgreSQL outperforms these LQOs in almost all experiments depending on the train/test splits. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/30586 |
| Fulltext version: | Published version |
| License (according to publishing contract): | Licence according to publishing contract |
| Departement: | School of Engineering |
| Organisational Unit: | Institute of Computer Science (InIT) |
| Published as part of the ZHAW project: | GraphQueryML – Verwendung von maschinellem Lernen zur Optimierung von Abfragen in Graphdatenbanken (SNF/DFG) |
| Appears in collections: | Publikationen School of Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2024_Lehmann-etal_Learned-query-optimizers_VLDB.pdf | 693.26 kB | Adobe PDF | View/Open |
Show full item record
Lehmann, C., Sulimov, P., & Stockinger, K. (2024). Is your learned query optimizer behaving as you expect? : a machine learning perspective. Proceedings of the VLDB Endowment, 17(7), 1565–1577. https://doi.org/10.21256/zhaw-30586
Lehmann, C., Sulimov, P. and Stockinger, K. (2024) ‘Is your learned query optimizer behaving as you expect? : a machine learning perspective’, Proceedings of the VLDB Endowment, 17(7), pp. 1565–1577. Available at: https://doi.org/10.21256/zhaw-30586.
C. Lehmann, P. Sulimov, and K. Stockinger, “Is your learned query optimizer behaving as you expect? : a machine learning perspective,” Proceedings of the VLDB Endowment, vol. 17, no. 7, pp. 1565–1577, Mar. 2024, doi: 10.21256/zhaw-30586.
LEHMANN, Claude, Pavel SULIMOV und Kurt STOCKINGER, 2024. Is your learned query optimizer behaving as you expect? : a machine learning perspective. Proceedings of the VLDB Endowment. März 2024. Bd. 17, Nr. 7, S. 1565–1577. DOI 10.21256/zhaw-30586
Lehmann, Claude, Pavel Sulimov, and Kurt Stockinger. 2024. “Is Your Learned Query Optimizer Behaving as You Expect? : A Machine Learning Perspective.” Proceedings of the VLDB Endowment 17 (7): 1565–77. https://doi.org/10.21256/zhaw-30586.
Lehmann, Claude, et al. “Is Your Learned Query Optimizer Behaving as You Expect? : A Machine Learning Perspective.” Proceedings of the VLDB Endowment, vol. 17, no. 7, Mar. 2024, pp. 1565–77, https://doi.org/10.21256/zhaw-30586.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.