Quantum Machine Learning for Join Order Optimization using Variational Quantum Circuits.

Tobias Winker; Umut Çalikyilmaz; Le Gruenwald; Sven Groppe

doi:10.1145/3579142.3594299

Quantum Machine Learning for Join Order Optimization using Variational Quantum Circuits.

Tobias Winker, Umut Çalikyilmaz, Le Gruenwald, Sven Groppe

Abstract

The optimization of queries speeds up query processing in databases. One of the most time-consuming tasks in query processing is the join operation, where the order of the joins plays a crucial role in determining the number of tuples to be processed for intermediate results, and hence, the overall processing costs. In this paper, we use a variational quantum circuit (VQC) to create a hybrid classical-quantum machine learning algorithm to predict efficient join orders by learning from past join orders. We develop an encoding of the join order problem using a low number of qubits. We show that VQCs with filtering of cross joins outperform the classical dynamic programming optimizer of PostgreSQL with a 2.7\% faster execution time.

Original language	English
Title of host publication	BiDEDE@SIGMOD
Number of pages	7
Publication date	2023
Pages	5:1-5:7
DOIs	https://doi.org/10.1145/3579142.3594299
Publication status	Published - 2023

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 4 Quality Education
SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities
SDG 12 Responsible Consumption and Production
SDG 14 Life Below Water
SDG 15 Life on Land

Research Areas and Centers

Centers: Center for Artificial Intelligence Luebeck (ZKIL)
Research Area: Intelligent Systems

DFG Research Classification Scheme

409-06 Information Systems, Process and Knowledge Management

Access to Document

10.1145/3579142.3594299

Cite this

@inproceedings{0e7a54edcc8f465db6e70042c6364bf7,

title = "Quantum Machine Learning for Join Order Optimization using Variational Quantum Circuits.",

abstract = "The optimization of queries speeds up query processing in databases. One of the most time-consuming tasks in query processing is the join operation, where the order of the joins plays a crucial role in determining the number of tuples to be processed for intermediate results, and hence, the overall processing costs. In this paper, we use a variational quantum circuit (VQC) to create a hybrid classical-quantum machine learning algorithm to predict efficient join orders by learning from past join orders. We develop an encoding of the join order problem using a low number of qubits. We show that VQCs with filtering of cross joins outperform the classical dynamic programming optimizer of PostgreSQL with a 2.7\textbackslash{}\% faster execution time.",

author = "Tobias Winker and Umut {\c C}alikyilmaz and Le Gruenwald and Sven Groppe",

note = "DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",

year = "2023",

doi = "10.1145/3579142.3594299",

language = "English",

pages = "5:1--5:7",

booktitle = "BiDEDE@SIGMOD",

}

TY - GEN

T1 - Quantum Machine Learning for Join Order Optimization using Variational Quantum Circuits.

AU - Winker, Tobias

AU - Çalikyilmaz, Umut

AU - Gruenwald, Le

AU - Groppe, Sven

N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2023

Y1 - 2023

N2 - The optimization of queries speeds up query processing in databases. One of the most time-consuming tasks in query processing is the join operation, where the order of the joins plays a crucial role in determining the number of tuples to be processed for intermediate results, and hence, the overall processing costs. In this paper, we use a variational quantum circuit (VQC) to create a hybrid classical-quantum machine learning algorithm to predict efficient join orders by learning from past join orders. We develop an encoding of the join order problem using a low number of qubits. We show that VQCs with filtering of cross joins outperform the classical dynamic programming optimizer of PostgreSQL with a 2.7\% faster execution time.

AB - The optimization of queries speeds up query processing in databases. One of the most time-consuming tasks in query processing is the join operation, where the order of the joins plays a crucial role in determining the number of tuples to be processed for intermediate results, and hence, the overall processing costs. In this paper, we use a variational quantum circuit (VQC) to create a hybrid classical-quantum machine learning algorithm to predict efficient join orders by learning from past join orders. We develop an encoding of the join order problem using a low number of qubits. We show that VQCs with filtering of cross joins outperform the classical dynamic programming optimizer of PostgreSQL with a 2.7\% faster execution time.

UR - https://www.mendeley.com/catalogue/4b1d308b-a103-3767-bfcc-c696b2b9ba1c/

U2 - 10.1145/3579142.3594299

DO - 10.1145/3579142.3594299

M3 - Conference contribution

SP - 5:1-5:7

BT - BiDEDE@SIGMOD

ER -

Quantum Machine Learning for Join Order Optimization using Variational Quantum Circuits.

Abstract

UN SDGs

Research Areas and Centers

DFG Research Classification Scheme

Access to Document

Other files and links

Cite this