Generating Multi-Categorical Samples with Generative Adversarial Networks
By Ramiro Daniel Camino, Christian Hammerschmidt, Radu State. 2018
82 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Alfredo Cuesta-Infante
- Lei Xu
- Vadim Borisov
- Gjergji Kasneci
- Kalyan Veeramachaneni
- Lei Xu
- Tobias Leemann
- Maria Skoularidou
In Computer Vision and Pattern Recognition
- Vadim Borisov
- Gjergji Kasneci
- Tobias Leemann
- Kathrin Sessler
- Martin Pawelczyk
- Alfredo Cuesta-Infante
- Lei Xu
- Kalyan Veeramachaneni
Citations in the corpus
- Synthesizing Tabular Data using Generative Adversarial Networks (2018, background): “RGAN and RCGAN [13] can generate real-valued time-series data. medGAN [9], corrGAN [33] and several improved models [2, 6, 47, 3, 44] can generate discrete medical records but do not tackle the complexity in generating multimodal continuous variables. ehrGAN [8] generates augmented medical records…”
- Deep Neural Networks and Tabular Data: A Survey (2021, background): “Another approach is to visually inspect the modeled distributions per feature, e.g., the cumulative distribution functions [117], or compare the expected values in scatter plots [39], [148].”
- Generation and evaluation of synthetic patient data (2020, methodology): “In this paper we adopt the multi-categorical extension of medGAN, called MC-MedGAN [28] to generate synthetic data related to cancer.”
- Modeling Tabular data using Conditional GAN (2019, methodology): “GANs are also used in generating tabular data, especially healthcare records; for example, [25] uses GANs to generate continuous time-series medical records and [4] proposes the generation of discrete tabular data using GANs.”