Quantum Split Learning for Privacy-Preserving Information Management

Soohyun Park; Hankyul Baek; Joongheon Kim

doi:10.1145/3583780.3615144

Quantum Split Learning for Privacy-Preserving Information Management

Soohyun Park
, Hankyul Baek
, Joongheon Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Citations (Scopus)

Abstract

Recently, research on quantum neural network (QNN) architectures has been attracted in various fields. Among them, the distributed computation of QNN has been actively discussed for privacy-preserving information management due to data and model distribution over multiple computing devices. Based on this concept, this paper proposes quantum split learning (QSL) which splits a single QNN architecture across multiple distributed computing devices to avoid entire QNN architecture exposure. In order to realize QSL design, this paper also proposes cross-channel pooling, which utilizes quantum state tomography. Our evaluation results verifies that QSL preserves privacy in classification tasks and also improves accuracy at most by 6.83% compared to existing methods.

Original language	English
Title of host publication	CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
Publisher	Association for Computing Machinery
Pages	4239-4243
Number of pages	5
ISBN (Electronic)	9798400701245
DOIs	https://doi.org/10.1145/3583780.3615144
Publication status	Published - 2023 Oct 21
Event	32nd ACM International Conference on Information and Knowledge Management, CIKM 2023 - Birmingham, United Kingdom Duration: 2023 Oct 21 → 2023 Oct 25

Publication series

Name	International Conference on Information and Knowledge Management, Proceedings

Conference

Conference	32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
Country/Territory	United Kingdom
City	Birmingham
Period	23/10/21 → 23/10/25

Bibliographical note

Publisher Copyright:
© 2023 Copyright held by the owner/author(s).

Keywords

Distributed Machine Learning
Quantum Machine Learning
Quantum Neural Networks
Split Learning

ASJC Scopus subject areas

General Business,Management and Accounting
General Decision Sciences

Access to Document

10.1145/3583780.3615144

Cite this

Park, S., Baek, H., & Kim, J. (2023). Quantum Split Learning for Privacy-Preserving Information Management. In CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (pp. 4239-4243). (International Conference on Information and Knowledge Management, Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3583780.3615144

Quantum Split Learning for Privacy-Preserving Information Management. / Park, Soohyun; Baek, Hankyul; Kim, Joongheon.
CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2023. p. 4239-4243 (International Conference on Information and Knowledge Management, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Park, S, Baek, H & Kim, J 2023, Quantum Split Learning for Privacy-Preserving Information Management. in CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, Association for Computing Machinery, pp. 4239-4243, 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023, Birmingham, United Kingdom, 23/10/21. https://doi.org/10.1145/3583780.3615144

@inproceedings{1b2f196d48b84a32bb3211c3c1e82e24,

title = "Quantum Split Learning for Privacy-Preserving Information Management",

abstract = "Recently, research on quantum neural network (QNN) architectures has been attracted in various fields. Among them, the distributed computation of QNN has been actively discussed for privacy-preserving information management due to data and model distribution over multiple computing devices. Based on this concept, this paper proposes quantum split learning (QSL) which splits a single QNN architecture across multiple distributed computing devices to avoid entire QNN architecture exposure. In order to realize QSL design, this paper also proposes cross-channel pooling, which utilizes quantum state tomography. Our evaluation results verifies that QSL preserves privacy in classification tasks and also improves accuracy at most by 6.83\% compared to existing methods.",

keywords = "Distributed Machine Learning, Quantum Machine Learning, Quantum Neural Networks, Split Learning",

author = "Soohyun Park and Hankyul Baek and Joongheon Kim",

note = "Publisher Copyright: {\textcopyright} 2023 Copyright held by the owner/author(s).; 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023 ; Conference date: 21-10-2023 Through 25-10-2023",

year = "2023",

month = oct,

day = "21",

doi = "10.1145/3583780.3615144",

language = "English",

series = "International Conference on Information and Knowledge Management, Proceedings",

publisher = "Association for Computing Machinery",

pages = "4239--4243",

booktitle = "CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management",

}

TY - GEN

T1 - Quantum Split Learning for Privacy-Preserving Information Management

AU - Park, Soohyun

AU - Baek, Hankyul

AU - Kim, Joongheon

PY - 2023/10/21

Y1 - 2023/10/21

N2 - Recently, research on quantum neural network (QNN) architectures has been attracted in various fields. Among them, the distributed computation of QNN has been actively discussed for privacy-preserving information management due to data and model distribution over multiple computing devices. Based on this concept, this paper proposes quantum split learning (QSL) which splits a single QNN architecture across multiple distributed computing devices to avoid entire QNN architecture exposure. In order to realize QSL design, this paper also proposes cross-channel pooling, which utilizes quantum state tomography. Our evaluation results verifies that QSL preserves privacy in classification tasks and also improves accuracy at most by 6.83% compared to existing methods.

AB - Recently, research on quantum neural network (QNN) architectures has been attracted in various fields. Among them, the distributed computation of QNN has been actively discussed for privacy-preserving information management due to data and model distribution over multiple computing devices. Based on this concept, this paper proposes quantum split learning (QSL) which splits a single QNN architecture across multiple distributed computing devices to avoid entire QNN architecture exposure. In order to realize QSL design, this paper also proposes cross-channel pooling, which utilizes quantum state tomography. Our evaluation results verifies that QSL preserves privacy in classification tasks and also improves accuracy at most by 6.83% compared to existing methods.

KW - Distributed Machine Learning

KW - Quantum Machine Learning

KW - Quantum Neural Networks

KW - Split Learning

UR - https://www.scopus.com/pages/publications/85178106150

U2 - 10.1145/3583780.3615144

DO - 10.1145/3583780.3615144

M3 - Conference contribution

AN - SCOPUS:85178106150

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 4239

EP - 4243

BT - CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management

PB - Association for Computing Machinery

T2 - 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023

Y2 - 21 October 2023 through 25 October 2023

ER -

Quantum Split Learning for Privacy-Preserving Information Management

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this