OCT-GAN: Neural ODE-based conditional tabular GANs

Jayoung Kim, Jinsung Jeon, Jaehoon Lee, Jihyeon Hyeong, Noseong Park

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

13 Citations (Scopus)

Abstract

Synthesizing tabular data is attracting much attention these days for various purposes. With sophisticate synthetic data, for instance, one can augment its training data. For the past couple of years, tabular data synthesis techniques have been greatly improved. Recent work made progress to address many problems in synthesizing tabular data, such as the imbalanced distribution and multimodality problems. However, the data utility of state-of-the-art methods is not satisfactory yet. In this work, we significantly improve the utility by designing our generator and discriminator based on neural ordinary differential equations (NODEs). After showing that NODEs have theoretically preferred characteristics for generating tabular data, we introduce our designs. The NODE-based discriminator performs a hidden vector evolution trajectory-based classification rather than classifying with a hidden vector at the last layer only. Our generator also adopts an ODE layer at the very beginning of its architecture to transform its initial input vector (i.e., the concatenation of a noisy vector and a condition vector in our case) onto another latent vector space suitable for the generation process. We conduct experiments with 13 datasets, including but not limited to insurance fraud detection, online news article prediction, and so on, and our presented method outperforms other state-of-the-art tabular data synthesis methods in many cases of our classification, regression, and clustering experiments.

Original languageEnglish
Title of host publicationThe Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021
PublisherAssociation for Computing Machinery, Inc
Pages1506-1515
Number of pages10
ISBN (Electronic)9781450383127
DOIs
Publication statusPublished - 2021 Apr 19
Event2021 World Wide Web Conference, WWW 2021 - Ljubljana, Slovenia
Duration: 2021 Apr 192021 Apr 23

Publication series

NameThe Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021

Conference

Conference2021 World Wide Web Conference, WWW 2021
Country/TerritorySlovenia
CityLjubljana
Period21/4/1921/4/23

Bibliographical note

Publisher Copyright:
© 2021 ACM.

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software

Fingerprint

Dive into the research topics of 'OCT-GAN: Neural ODE-based conditional tabular GANs'. Together they form a unique fingerprint.

Cite this