Anomaly detection with variational quantum generative adversarial networks
Тип публикации: Journal Article
Дата публикации: 2021-07-09
scimago Q1
wos Q1
БС1
SJR: 1.911
CiteScore: 10.9
Impact factor: 5.0
ISSN: 20589565, 23649054, 23649062
Atomic and Molecular Physics, and Optics
Materials Science (miscellaneous)
Electrical and Electronic Engineering
Physics and Astronomy (miscellaneous)
Краткое описание
Generative adversarial networks (GANs) are a machine learning framework comprising a generative model for sampling from a target distribution and a discriminative model for evaluating the proximity of a sample to the target distribution. GANs exhibit strong performance in imaging or anomaly detection. However, they suffer from training instabilities, and sampling efficiency may be limited by the classical sampling procedure. We introduce variational quantum-classical Wasserstein GANs to address these issues and embed this model in a classical machine learning framework for anomaly detection. Classical Wasserstein GANs improve training stability by using a cost function better suited for gradient descent. Our model replaces the generator of Wasserstein GANs with a hybrid quantum-classical neural net and leaves the classical discriminative model unchanged. This way, high-dimensional classical data only enters the classical model and need not be prepared in a quantum circuit. We demonstrate the effectiveness of this method on a credit card fraud dataset. For this dataset our method shows performance on par with classical methods in terms of the $F_1$ score. We analyze the influence of the circuit ansatz, layer width and depth, neural net architecture parameter initialization strategy, and sampling noise on convergence and performance.
Найдено
Ничего не найдено, попробуйте изменить настройки фильтра.
Найдено
Ничего не найдено, попробуйте изменить настройки фильтра.
Топ-30
Журналы
|
1
2
3
|
|
|
IEEE Transactions on Quantum Engineering
3 публикации, 7.14%
|
|
|
Physical Review A
2 публикации, 4.76%
|
|
|
Advanced Quantum Technologies
2 публикации, 4.76%
|
|
|
Future Generation Computer Systems
2 публикации, 4.76%
|
|
|
IEEE Access
2 публикации, 4.76%
|
|
|
EPJ Quantum Technology
2 публикации, 4.76%
|
|
|
Quantum Science and Technology
2 публикации, 4.76%
|
|
|
Machine Learning: Science and Technology
2 публикации, 4.76%
|
|
|
Physical Review Applied
1 публикация, 2.38%
|
|
|
Advances in Physics: X
1 публикация, 2.38%
|
|
|
Scientific Reports
1 публикация, 2.38%
|
|
|
Procedia Computer Science
1 публикация, 2.38%
|
|
|
Neurocomputing
1 публикация, 2.38%
|
|
|
Physica A: Statistical Mechanics and its Applications
1 публикация, 2.38%
|
|
|
Annales Henri Poincare
1 публикация, 2.38%
|
|
|
Physical Review B
1 публикация, 2.38%
|
|
|
Expert Systems with Applications
1 публикация, 2.38%
|
|
|
Journal of Systems and Software
1 публикация, 2.38%
|
|
|
Electronics (Switzerland)
1 публикация, 2.38%
|
|
|
Quantum Machine Intelligence
1 публикация, 2.38%
|
|
|
Visual Computer
1 публикация, 2.38%
|
|
|
Chinese Journal of Physics
1 публикация, 2.38%
|
|
|
Physical Review Research
1 публикация, 2.38%
|
|
|
1
2
3
|
Издатели
|
2
4
6
8
10
12
14
16
|
|
|
Institute of Electrical and Electronics Engineers (IEEE)
15 публикаций, 35.71%
|
|
|
Elsevier
8 публикаций, 19.05%
|
|
|
Springer Nature
6 публикаций, 14.29%
|
|
|
American Physical Society (APS)
5 публикаций, 11.9%
|
|
|
IOP Publishing
4 публикации, 9.52%
|
|
|
Wiley
2 публикации, 4.76%
|
|
|
Taylor & Francis
1 публикация, 2.38%
|
|
|
MDPI
1 публикация, 2.38%
|
|
|
2
4
6
8
10
12
14
16
|
- Мы не учитываем публикации, у которых нет DOI.
- Статистика публикаций обновляется еженедельно.
Вы ученый?
Создайте профиль, чтобы получать персональные рекомендации коллег, конференций и новых статей.
Метрики
42
Всего цитирований:
42
Цитирований c 2024:
26
(61.9%)
Цитировать
ГОСТ |
RIS |
BibTex |
MLA
Цитировать
ГОСТ
Скопировать
Herr D., Obert B., Rosenkranz M. Anomaly detection with variational quantum generative adversarial networks // Quantum Science and Technology. 2021. Vol. 6. No. 4. p. 45004.
ГОСТ со всеми авторами (до 50)
Скопировать
Herr D., Obert B., Rosenkranz M. Anomaly detection with variational quantum generative adversarial networks // Quantum Science and Technology. 2021. Vol. 6. No. 4. p. 45004.
Цитировать
RIS
Скопировать
TY - JOUR
DO - 10.1088/2058-9565/ac0d4d
UR - https://doi.org/10.1088/2058-9565/ac0d4d
TI - Anomaly detection with variational quantum generative adversarial networks
T2 - Quantum Science and Technology
AU - Herr, Daniel
AU - Obert, Benjamin
AU - Rosenkranz, Matthias
PY - 2021
DA - 2021/07/09
PB - IOP Publishing
SP - 45004
IS - 4
VL - 6
SN - 2058-9565
SN - 2364-9054
SN - 2364-9062
ER -
Цитировать
BibTex (до 50 авторов)
Скопировать
@article{2021_Herr,
author = {Daniel Herr and Benjamin Obert and Matthias Rosenkranz},
title = {Anomaly detection with variational quantum generative adversarial networks},
journal = {Quantum Science and Technology},
year = {2021},
volume = {6},
publisher = {IOP Publishing},
month = {jul},
url = {https://doi.org/10.1088/2058-9565/ac0d4d},
number = {4},
pages = {45004},
doi = {10.1088/2058-9565/ac0d4d}
}
Цитировать
MLA
Скопировать
Herr, Daniel, et al. “Anomaly detection with variational quantum generative adversarial networks.” Quantum Science and Technology, vol. 6, no. 4, Jul. 2021, p. 45004. https://doi.org/10.1088/2058-9565/ac0d4d.