Generating Multi-Categorical Samples with Generative Adversarial Networks
arXiv:1807.01202
Abstract
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.
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Categorical Reparameterization with Gumbel-Softmax
- Improved Training of Wasserstein GANs
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Which Training Methods for GANs do actually Converge?
- A note on the evaluation of generative models
- Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
- GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
- Adversarially Regularized Autoencoders
Cited by in corpus (11)
- Synthesizing Tabular Data using Generative Adversarial Networks
- A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models
- Modeling Tabular data using Conditional GAN
- A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources
- Controllable Data Generation by Deep Learning: A Review
- Improving Missing Data Imputation with Deep Generative Models
- Synthetic Observational Health Data with GANs: from slow adoption to a boom in medical research and ultimately digital twins?
- Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networks
- Causal Adversarial Network for Learning Conditional and Interventional Distributions
- Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
- Minority Class Oversampling for Tabular Data with Deep Generative Models