A Survey of Missing Data Imputation Using Generative Adversarial Networks

Jaeyoon Kim; Donghyun Tae; Junhee Seok

doi:10.1109/ICAIIC48513.2020.9065044

A Survey of Missing Data Imputation Using Generative Adversarial Networks

Jaeyoon Kim, Donghyun Tae, Junhee Seok

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

30 Citations (Scopus)

Abstract

Recently, many deep learning models for missing data imputation have been studied. One of the most popular models is Generative Adversarial Networks (GANs), which generate plausible fake data through adversarial training. In this paper, we take a look at the architecture, objective of a generator and a discriminator, training method and loss function. After that, we can see what improvements have been made to each model. Moreover, we can easily compare several GAN-based models for missing data imputation.

Original language	English
Title of host publication	2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	454-456
Number of pages	3
ISBN (Electronic)	9781728149851
DOIs	https://doi.org/10.1109/ICAIIC48513.2020.9065044
Publication status	Published - 2020 Feb 1
Event	2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020 - Fukuoka, Japan Duration: 2020 Feb 19 → 2020 Feb 21

Publication series

Name	2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

Conference

Conference	2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020
Country/Territory	Japan
City	Fukuoka
Period	20/2/19 → 20/2/21

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

Adversarial training
Discriminator
Generative Adversarial Networks (GANs)
Generator
Missing data imputation

ASJC Scopus subject areas

Information Systems and Management
Artificial Intelligence
Computer Networks and Communications
Computer Vision and Pattern Recognition
Information Systems
Signal Processing

Access to Document

10.1109/ICAIIC48513.2020.9065044

Cite this

Kim, J., Tae, D., & Seok, J. (2020). A Survey of Missing Data Imputation Using Generative Adversarial Networks. In 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020 (pp. 454-456). Article 9065044 (2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAIIC48513.2020.9065044

A Survey of Missing Data Imputation Using Generative Adversarial Networks. / Kim, Jaeyoon; Tae, Donghyun; Seok, Junhee.
2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 454-456 9065044 (2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020).

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

Kim, J, Tae, D & Seok, J 2020, A Survey of Missing Data Imputation Using Generative Adversarial Networks. in 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020., 9065044, 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020, Institute of Electrical and Electronics Engineers Inc., pp. 454-456, 2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020, Fukuoka, Japan, 20/2/19. https://doi.org/10.1109/ICAIIC48513.2020.9065044

Kim J, Tae D, Seok J. A Survey of Missing Data Imputation Using Generative Adversarial Networks. In 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 454-456. 9065044. (2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020). doi: 10.1109/ICAIIC48513.2020.9065044

Kim, Jaeyoon ; Tae, Donghyun ; Seok, Junhee. / A Survey of Missing Data Imputation Using Generative Adversarial Networks. 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 454-456 (2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020).

@inproceedings{73ecf7b4f93c478f9532a606124cef39,

title = "A Survey of Missing Data Imputation Using Generative Adversarial Networks",

abstract = "Recently, many deep learning models for missing data imputation have been studied. One of the most popular models is Generative Adversarial Networks (GANs), which generate plausible fake data through adversarial training. In this paper, we take a look at the architecture, objective of a generator and a discriminator, training method and loss function. After that, we can see what improvements have been made to each model. Moreover, we can easily compare several GAN-based models for missing data imputation.",

keywords = "Adversarial training, Discriminator, Generative Adversarial Networks (GANs), Generator, Missing data imputation",

author = "Jaeyoon Kim and Donghyun Tae and Junhee Seok",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020 ; Conference date: 19-02-2020 Through 21-02-2020",

year = "2020",

month = feb,

day = "1",

doi = "10.1109/ICAIIC48513.2020.9065044",

language = "English",

series = "2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "454--456",

booktitle = "2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020",

}

TY - GEN

T1 - A Survey of Missing Data Imputation Using Generative Adversarial Networks

AU - Kim, Jaeyoon

AU - Tae, Donghyun

AU - Seok, Junhee

PY - 2020/2/1

Y1 - 2020/2/1

N2 - Recently, many deep learning models for missing data imputation have been studied. One of the most popular models is Generative Adversarial Networks (GANs), which generate plausible fake data through adversarial training. In this paper, we take a look at the architecture, objective of a generator and a discriminator, training method and loss function. After that, we can see what improvements have been made to each model. Moreover, we can easily compare several GAN-based models for missing data imputation.

AB - Recently, many deep learning models for missing data imputation have been studied. One of the most popular models is Generative Adversarial Networks (GANs), which generate plausible fake data through adversarial training. In this paper, we take a look at the architecture, objective of a generator and a discriminator, training method and loss function. After that, we can see what improvements have been made to each model. Moreover, we can easily compare several GAN-based models for missing data imputation.

KW - Adversarial training

KW - Discriminator

KW - Generative Adversarial Networks (GANs)

KW - Generator

KW - Missing data imputation

UR - http://www.scopus.com/inward/record.url?scp=85084035336&partnerID=8YFLogxK

U2 - 10.1109/ICAIIC48513.2020.9065044

DO - 10.1109/ICAIIC48513.2020.9065044

M3 - Conference contribution

AN - SCOPUS:85084035336

T3 - 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

SP - 454

EP - 456

BT - 2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

Y2 - 19 February 2020 through 21 February 2020

ER -

A Survey of Missing Data Imputation Using Generative Adversarial Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this