A Survey of Missing Data Imputation Using Generative Adversarial Networks

Jaeyoon Kim, Donghyun Tae, Junhee Seok

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 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 languageEnglish
Title of host publication2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages454-456
Number of pages3
ISBN (Electronic)9781728149851
DOIs
Publication statusPublished - 2020 Feb 1
Event2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020 - Fukuoka, Japan
Duration: 2020 Feb 192020 Feb 21

Publication series

Name2020 International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

Conference

Conference2nd International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020
Country/TerritoryJapan
CityFukuoka
Period20/2/1920/2/21

Bibliographical note

Funding Information:
The correspondence should be addressed to jseok14@korea.ac.kr. This work was supported by grants from the National Research Foundation of Korea (NRF-2017R1C1B2002850, NRF-2019R1A2C1084778)

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

Fingerprint

Dive into the research topics of 'A Survey of Missing Data Imputation Using Generative Adversarial Networks'. Together they form a unique fingerprint.

Cite this