OCT-GAN: Neural ODE-based Conditional Tabular GANs

by   Jayoung Kim, et al.

Synthesizing tabular data is attracting much attention these days for various purposes. With sophisticate synthetic data, for instance, one can augment its training data. For the past couple of years, tabular data synthesis techniques have been greatly improved. Recent work made progress to address many problems in synthesizing tabular data, such as the imbalanced distribution and multimodality problems. However, the data utility of state-of-the-art methods is not satisfactory yet. In this work, we significantly improve the utility by designing our generator and discriminator based on neural ordinary differential equations (NODEs). After showing that NODEs have theoretically preferred characteristics for generating tabular data, we introduce our designs. The NODE-based discriminator performs a hidden vector evolution trajectory-based classification rather than classifying with a hidden vector at the last layer only. Our generator also adopts an ODE layer at the very beginning of its architecture to transform its initial input vector (i.e., the concatenation of a noisy vector and a condition vector in our case) onto another latent vector space suitable for the generation process. We conduct experiments with 13 datasets, including but not limited to insurance fraud detection, online news article prediction, and so on, and our presented method outperforms other state-of-the-art tabular data synthesis methods in many cases of our classification, regression, and clustering experiments.


GTV: Generating Tabular Data via Vertical Federated Learning

Generative Adversarial Networks (GANs) have achieved state-of-the-art re...

Data-Efficient Instance Generation from Instance Discrimination

Generative Adversarial Networks (GANs) have significantly advanced image...

FCT-GAN: Enhancing Table Synthesis via Fourier Transform

Synthetic tabular data emerges as an alternative for sharing knowledge w...

ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equations

Neural ordinary differential equations (NODEs) presented a new paradigm ...

CrossPyramid: Neural Ordinary Differential Equations Architecture for Partially-observed Time-series

Ordinary Differential Equations (ODE)-based models have become popular f...

Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling

We show that the sum of the implicit generator log-density log p_g of a ...

Study of Constrained Network Structures for WGANs on Numeric Data Generation

Some recent studies have suggested using GANs for numeric data generatio...

Please sign up or login with your details

Forgot password? Click here to reset