Modeling Tabular data using Conditional GAN

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 TGAN, which uses a conditional generative adversarial network 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. TGAN outperforms Bayesian methods on most of the real datasets whereas other deep learning methods could not.

arXiv commentAccepted to NeurIPS 2019

References in corpus (9)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• Categorical Reparameterization with Gumbel-Softmax
• Data Synthesis based on Generative Adversarial Networks
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• Generating Multi-Categorical Samples with Generative Adversarial Networks
• Generative Adversarial Networks for Electronic Health Records: A Framework for Exploring and Evaluating Methods for Predicting Drug-Induced Laboratory Test Trajectories
• Generating Synthetic but Plausible Healthcare Record Datasets

Cited by in corpus (12)

• Differentially Private Synthetic Data: Applied Evaluations and Enhancements
• AutoScore-Imbalance: An interpretable machine learning tool for development of clinical scores with rare events data
• Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration
• Improving LIME Robustness with Smarter Locality Sampling
• Generative Synthesis of Insurance Datasets
• Positive unlabeled learning with tensor networks
• An Analysis of the Deployment of Models Trained on Private Tabular Synthetic Data: Unexpected Surprises
• Holdout-Based Fidelity and Privacy Assessment of Mixed-Type Synthetic Data
• Transitioning from Real to Synthetic data: Quantifying the bias in model
• TableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing
• Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
• Generative Models for Security: Attacks, Defenses, and Opportunities