Skip to content
Research Article Open access CC BY 4.0

Generation and Evaluation of Tabular Data in Different Domains Using Gans

Persevearance Marecha, Lu Ye

Asian Journal of Research in Computer Science · pp. 15–27 · Published 24 May 2023

10.9734/ajrcos/2023/v16i1331

Abstract

Deep learning techniques like Generative Adversarial Networks (GANs) provide solutions in many domains where real data needs to be kept private. Synthesizing tabular data is difficult because of its high complexity. Tabular data usually contains a mixture of discrete and continuous data, which is not an easy model to build. The contributions made in this paper include training and generating data with the original Vanilla Gan, then CGan and WGan-Gp and WCGan-Gp which performs better than the former. The Adult Income Census dataset mainly focuses on predicting whether income exceeds 50,000 per year based on census data, then comparing the accuracy of machine learning models and calculating the F1 scores. Then the use of TimeGan on the stock dataset, comparing synthetic data vs real data. This paper will explore the use of GANs for generating and evaluating tabular data in different domains.

Generative adversarial networks tabular data synthetic

References (17)

  1. 1 Unsupervised K-Means Clustering Algorithm [DOI]
  2. 2 Generative adversarial network: An overview of theory and applications [DOI]
  3. 3 Machine Learning in Python: Main Developments and Technology Trends in Data Science, Machine Learning, and Artificial Intelligence [DOI]
  4. 4 TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks [DOI]
  5. 5 GANs for Medical Image Synthesis: An Empirical Study [DOI]
  6. 6 Data augmentation using Generative Adversarial Networks (GANs) for GAN-based detection of Pneumonia and COVID-19 in chest X-ray images [DOI]
  7. 7 A Review of Tabular Data Synthesis Using GANs on an IDS Dataset [DOI]
  8. 8 The use of generative adversarial networks to alleviate class imbalance in tabular data: a survey [DOI]
  9. 9 A Multi-step ahead photovoltaic power forecasting model based on TimeGAN, Soft DTW-based K-medoids clustering, and a CNN-GRU hybrid neural network [DOI]
  10. 10 Brain Tumor Classification using Machine Learning [DOI]
  11. 11 Impact on Inference Model Performance for ML Tasks Using Real-Life Training Data and Synthetic Training Data from GANs [DOI]
  12. 12 Multi-Style Unsupervised Image Synthesis Using Generative Adversarial Nets [DOI]
  13. 13 Ensemble Approach with Hyperparameter Tuning for Credit Worthiness Prediction [DOI]
  14. 14 Improving weight clipping in Wasserstein GANs [DOI]
  15. 15 High Fidelity GAN Inversion via Prior Multi-Subspace Feature Composition [DOI]
  16. 16 Generative adversarial networks in time series: A survey and taxonomy [DOI]
  17. 17 RCC-GAN: Regularized Compound Conditional GAN for Large-Scale Tabular Data Synthesis [DOI]

Cited by 10

Stable-Feature-Guided Degradation-Zone Adaptive Augmentation for UAV Hyperspectral Vegetation Degradation Monitoring

Liang-Chun Wang, Wen-Xia Zhang, Jian-Jun Li · 2026 5th International Symposium on Aerospace Engineering and Systems (ISAES) · 2026

Soil heavy metal prediction using GF-5 hyperspectral image and environmental covariates with data augmentation.

You-Xin Sun, Xia Zhang, Yaqiong Zhang · Journal of Hazardous Materials · 2026

Probabilistic Versus Deep Generative Models: A Fairness Centred Evaluation of Synthetic Healthcare Tabular Data

Dima R. Alattal, Barbara Draghi, Puja Myles · International Journal of Computational Intelligence Systems · 2026

Soil organic matter content prediction in tobacco fields based on hyperspectral remote sensing and generative adversarial network data augmentation

Yu Xia, Xueying Cheng, Xiao Hu · Computers and Electronics in Agriculture · 2025

Probabilistic vs Deep Generative Models: A Fairness Centred Evaluation of Synthetic Healthcare Tabular Data

Dima Alattal, Barbara Draghi, Puja Myles · 2025

Showing 5 of 10 known citations — external sources report more than can currently be individually listed.

Related research

Article metrics

Real usage data collected on this platform.

35

Page views

0

PDF downloads

4

Outbound clicks

10

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.