short-paper

Public Access

Learning State Representations for Query Optimization with Deep Reinforcement Learning

Authors:

Jennifer Ortiz,

Magdalena Balazinska,

Johannes Gehrke,

S. Sathiya KeerthiAuthors Info & Claims

DEEM'18: Proceedings of the Second Workshop on Data Management for End-To-End Machine Learning

Article No.: 4, Pages 1 - 4

https://doi.org/10.1145/3209889.3209890

Published: 15 June 2018 Publication History

PDF eReader

Abstract

We explore the idea of using deep reinforcement learning for query optimization. The approach is to build queries incrementally by encoding properties of subqueries using a learned representation.

In this paper, we focus specifically on the state representation problem and the formation of the state transition function. We show preliminary results and discuss how we can use the state representation to improve query optimization using reinforcement learning.

References

[1]

Martín Abadi et al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. Software available from tensorfow.org.

Google Scholar

[2]

Ron Avnur et al. Eddies: Continuously adaptive query processing. SIGMOD Record, 2000.

Digital Library

Google Scholar

[3]

Ian Goodfellow et al. Deep Learning. MIT Press, 2016. http://www.deeplearningbook.org.

Digital Library

Google Scholar

[4]

Tim Kraska et al. The case for learned index structures. CoRR, 2017.

Google Scholar

[5]

Viktor Leis et al. How good are query optimizers, really? Proc. VLDB Endow., 2015.

Digital Library

Google Scholar

[6]

Henry Liu et al. Cardinality estimation using neural networks. In CASCON 2015.

Google Scholar

[7]

Ryan Marcus et al. Deep reinforcement learning for join order enumeration. CoRR, 2018.

Google Scholar

[8]

Volodymyr Mnih et al. Human-level control through deep reinforcement learning. Nature, 2015.

Google Scholar

[9]

David Silver. UCL Course on Reinforcement Learning, 2015.

Google Scholar

[10]

Michael Stillger et al. Leo - db2's learning optimizer. In VLDB 2001.

Digital Library

Google Scholar

[11]

Richard S. Sutton et al. Reinforcement learning I: Introduction, 2016.

Google Scholar

[12]

Csaba Szepesvari. Algorithms for reinforcement learning. Morgan and Claypool Publishers, 2009.

Digital Library

Google Scholar

[13]

Kostas Tzoumas et al. A reinforcement learning approach for adaptive query processing. In A DB Technical Report, 2008.

Google Scholar

[14]

Wei Wang et al. Database Meets Deep Learning: Challenges and Opportunities. SIGMOD Record, 2016.

Digital Library

Google Scholar

Cited By

View all

Raghebi ZBanaei-Kashani F(2024)ActiveReach: an active learning framework for approximate reachability query answering in large-scale graphsFrontiers in Big Data10.3389/fdata.2024.14271047Online publication date: 19-Nov-2024
https://doi.org/10.3389/fdata.2024.1427104
Milicevic BBabovic Z(2024)A systematic review of deep learning applications in database query executionJournal of Big Data10.1186/s40537-024-01025-111:1Online publication date: 18-Dec-2024
https://doi.org/10.1186/s40537-024-01025-1
Kim KLee SKim IHan W(2024)ASM: Harmonizing Autoregressive Model, Sampling, and Multi-dimensional Statistics Merging for Cardinality EstimationProceedings of the ACM on Management of Data10.1145/36393002:1(1-27)Online publication date: 26-Mar-2024
https://dl.acm.org/doi/10.1145/3639300
Show More Cited By

Learning State Representations for Query Optimization with Deep Reinforcement Learning

Recommendations

Research challenges in deep reinforcement learning-based join query optimization
aiDM '20: Proceedings of the Third International Workshop on Exploiting Artificial Intelligence Techniques for Data Management

The order in which relations are joined and the physical join operators used are two aspects of query plans which have a significant impact on the execution latency of join queries. However, the set of valid query plans grows exponentially with the ...
Learning Global Optimization by Deep Reinforcement Learning
Intelligent Systems
Abstract
Learning to Optimize (L2O) is a growing field that employs a variety of machine learning (ML) methods to learn optimization algorithms automatically from data instead of developing hand-engineered algorithms that usually require hyperparameter ...
Coral: federated query join order optimization based on deep reinforcement learning
Abstract
The rise of diversified data engines has created the need for federated queries. A federated query can take a query and provide data analysis based on data from various data engines. Since the query data originates from multiple data engines, ...

Comments

Information & Contributors

Information

Published In

DEEM'18: Proceedings of the Second Workshop on Data Management for End-To-End Machine Learning

June 2018

63 pages

ISBN:9781450358286

DOI:10.1145/3209889

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 June 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Short-paper
Research
Refereed limited

Funding Sources

National Science Foundation

Conference

SIGMOD/PODS '18

Sponsor:

SIGMOD

SIGMOD/PODS '18: International Conference on Management of Data

June 15, 2018

TX, Houston, USA

Acceptance Rates

DEEM'18 Paper Acceptance Rate 10 of 16 submissions, 63%;

Overall Acceptance Rate 44 of 67 submissions, 66%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

79
Total Citations
View Citations
2,504
Total Downloads

Downloads (Last 12 months)286
Downloads (Last 6 weeks)42

Reflects downloads up to 30 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Raghebi ZBanaei-Kashani F(2024)ActiveReach: an active learning framework for approximate reachability query answering in large-scale graphsFrontiers in Big Data10.3389/fdata.2024.14271047Online publication date: 19-Nov-2024
https://doi.org/10.3389/fdata.2024.1427104
Milicevic BBabovic Z(2024)A systematic review of deep learning applications in database query executionJournal of Big Data10.1186/s40537-024-01025-111:1Online publication date: 18-Dec-2024
https://doi.org/10.1186/s40537-024-01025-1
Kim KLee SKim IHan W(2024)ASM: Harmonizing Autoregressive Model, Sampling, and Multi-dimensional Statistics Merging for Cardinality EstimationProceedings of the ACM on Management of Data10.1145/36393002:1(1-27)Online publication date: 26-Mar-2024
https://dl.acm.org/doi/10.1145/3639300
Huang XGao XChen G(2024)DITune: A Reinforcement Learning Based Framework for Automated Database Index Selection2024 18th International Conference on Ubiquitous Information Management and Communication (IMCOM)10.1109/IMCOM60618.2024.10418292(1-8)Online publication date: 3-Jan-2024
https://doi.org/10.1109/IMCOM60618.2024.10418292
Tie JPan ZSun CWu LHu YZhang BCao S(2024)QFEDS: A GNN-Based Query Featurization Enhancement Method for Cardinality Estimation2024 IEEE International Conference on e-Business Engineering (ICEBE)10.1109/ICEBE62490.2024.00054(306-311)Online publication date: 11-Oct-2024
https://doi.org/10.1109/ICEBE62490.2024.00054
Ya HSun CTie JWu LRuan CHu YZhang BCao S(2024)MQPHFM: A SQL Query Featurization Method Suitable for Cardinality Estimation Tasks2024 IEEE International Conference on e-Business Engineering (ICEBE)10.1109/ICEBE62490.2024.00020(74-80)Online publication date: 11-Oct-2024
https://doi.org/10.1109/ICEBE62490.2024.00020
Feng JLi ZChen Q(2024)Towards Exploratory Query Optimization for Template-Based SQL Workloads2024 IEEE 40th International Conference on Data Engineering (ICDE)10.1109/ICDE60146.2024.00019(151-164)Online publication date: 13-May-2024
https://doi.org/10.1109/ICDE60146.2024.00019
Xiong XYu JHe Z(2024)AutoQuo: An Adaptive plan optimizer with reinforcement learning for query plan selectionKnowledge-Based Systems10.1016/j.knosys.2024.112664(112664)Online publication date: Nov-2024
https://doi.org/10.1016/j.knosys.2024.112664
Peng JShen DNie TKou Y(2024)RLclean: An Unsupervised Integrated Data Cleaning Framework Based on Deep Reinforcement LearningInformation Sciences10.1016/j.ins.2024.121281(121281)Online publication date: Jul-2024
https://doi.org/10.1016/j.ins.2024.121281
Li YWang LWang SSun YZheng BPeng Z(2024)A Learned Cost Model for Big Data Query ProcessingInformation Sciences10.1016/j.ins.2024.120650(120650)Online publication date: Apr-2024
https://doi.org/10.1016/j.ins.2024.120650
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Recommendations

Research challenges in deep reinforcement learning-based join query optimization

Learning Global Optimization by Deep Reinforcement Learning

Coral: federated query join order optimization based on deep reinforcement learning

Comments

Published In

Sponsors

Publisher

Publication History

Permissions

Check for updates

Qualifiers

Funding Sources

Conference

Acceptance Rates

Other Metrics

Article Metrics

Other Metrics

Cited By

PDF

eReader

Login options

Full Access

Abstract

References

Cited By

Recommendations

Research challenges in deep reinforcement learning-based join query optimization

Learning Global Optimization by Deep Reinforcement Learning

Coral: federated query join order optimization based on deep reinforcement learning

Comments

Information

Published In

Sponsors

Publisher

Publication History

Permissions

Check for updates

Qualifiers

Funding Sources

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

PDF

eReader

Login options

Full Access

Share

Share this Publication link

Share on social media

Affiliations