Modeling tabular data using conditional GAN. Xu, L., Skoularidou, M., Cuesta-Infante, A., & Veeramachaneni, K. *Advances in Neural Information Processing Systems*, 32:7335–7345, 2019. ISSN: 10495258 _eprint: 1907.00503Paper abstract bibtex Modeling the probability distribution of rows in tabular data and generating realistic synthetic data is a non-trivial task. Tabular data usually contains a mix of discrete and continuous columns. Continuous columns may have multiple modes whereas discrete columns are sometimes imbalanced making the modeling difficult. Existing statistical and deep neural network models fail to properly model this type of data. We design CTGAN, which uses a conditional generator to address these challenges. To aid in a fair and thorough comparison, we design a benchmark with 7 simulated and 8 real datasets and several Bayesian network baselines. CTGAN outperforms Bayesian methods on most of the real datasets whereas other deep learning methods could not.

@article{xu_modeling_2019,
title = {Modeling tabular data using conditional {GAN}},
volume = {32},
url = {http://papers.nips.cc/paper/8953-modeling-tabular-data-using-conditional-gan.pdf https://papers.nips.cc/paper/8953-modeling-tabular-data-using-conditional-gan.pdf All Papers/X/Xu et al. 2019 - Modeling Tabular data using Conditional GAN.pdf},
abstract = {Modeling the probability distribution of rows in tabular data and generating realistic synthetic data is a non-trivial task. Tabular data usually contains a mix of discrete and continuous columns. Continuous columns may have multiple modes whereas discrete columns are sometimes imbalanced making the modeling difficult. Existing statistical and deep neural network models fail to properly model this type of data. We design CTGAN, which uses a conditional generator to address these challenges. To aid in a fair and thorough comparison, we design a benchmark with 7 simulated and 8 real datasets and several Bayesian network baselines. CTGAN outperforms Bayesian methods on most of the real datasets whereas other deep learning methods could not.},
journal = {Advances in Neural Information Processing Systems},
author = {Xu, Lei and Skoularidou, Maria and Cuesta-Infante, Alfredo and Veeramachaneni, Kalyan},
editor = {Wallach, H and Larochelle, H and Beygelzimer, A and d\${\textbackslash}backslash\$textquotesingle Alché-Buc, F and Fox, E and Garnett, R},
year = {2019},
note = {ISSN: 10495258
\_eprint: 1907.00503},
keywords = {Unsorted},
pages = {7335--7345},
}