mlsanityData to 7 Oct 2026

Generating Multi-Categorical Samples with Generative Adversarial Networks

arXiv 1807.01202 ↗First posted 3 Jul 2018stat.ML cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

We propose a method to train generative adversarial networks on mutivariate feature vectors representing multiple categorical values. In contrast to the continuous domain, where GAN-based methods have delivered considerable results, GANs struggle to perform equally well on discrete data. We propose and compare several architectures based on multiple (Gumbel) softmax output layers taking into account the structure of the data. We evaluate the performance of our architecture on datasets with different sparsity, number of features, ranges of categorical values, and dependencies among the features. Our proposed architecture and method outperforms existing models.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 8; 2023: 2; 2024: 2; 2025: 1.

17 papers.

Sort:

By area:

  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  2. 2022A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Modelscited by 43
  3. 2024How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Datacited by 29
  4. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  5. 2022A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sourcescited by 13
  6. 2021Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networkscited by 12
  7. 2022Generating Synthetic Clinical Data that Capture Class Imbalanced Distributions with Generative Adversarial Networks: Example using Antiretroviral Therapy for HIVcited by 12
  8. 2023Synthetic Health-related Longitudinal Data with Mixed-type Variables Generated using Diffusion Modelscited by 9
  9. 2021Generative Adversarial Networks for Synthetic Data Generation: A Comparative Studycited by 5
  10. 2022Comparing the Utility and Disclosure Risk of Synthetic Data with Samples of Microdatacited by 4
  11. 2021Bi-Discriminator Class-Conditional Tabular GANcited by 3
  12. 2022Generative Modeling of Complex Datacited by 3
5 more
  1. 2022Privacy-Utility Trades in Crowdsourced Signal Map Obfuscationcited by 2
  2. 2024A Unified Framework for Tabular Generative Modeling: Loss Functions, Benchmarks, and Improved Multi-objective Bayesian Optimization Approachescited by 2
  3. 2022FinGAN: Generative Adversarial Network for Analytical Customer Relationship Management in Banking and Insurancecited by 1
  4. 2025Assessing Generative Models for Structured Datacited by 1
  5. 2023Joint Distributional Learning via Cramer-Wold Distancecited by 0