Composable Generative Models

TL;DR

This paper introduces the Composable Generative Model (CGM), a flexible architecture for synthetic data generation that excels in tabular data and can incorporate various conditional models, with applications in privacy-preserving data analysis.

Contribution

The paper presents a novel, state-of-the-art composable architecture for generative modeling, capable of handling diverse data types and outperforming existing models in tabular data generation.

Findings

CGM outperforms 14 recent models on 13 datasets.

It effectively generates numerical, categorical, image, text, and time series data.

The model is suitable for privacy-preserving data analysis applications.

Abstract

Generative modeling has recently seen many exciting developments with the advent of deep generative architectures such as Variational Auto-Encoders (VAE) or Generative Adversarial Networks (GAN). The ability to draw synthetic i.i.d. observations with the same joint probability distribution as a given dataset has a wide range of applications including representation learning, compression or imputation. It appears that it also has many applications in privacy preserving data analysis, especially when used in conjunction with differential privacy techniques. This paper focuses on synthetic data generation models with privacy preserving applications in mind. It introduces a novel architecture, the Composable Generative Model (CGM) that is state-of-the-art in tabular data generation. Any conditional generative model can be used as a sub-component of the CGM, including CGMs themselves, allowing the generation of numerical, categorical data as well as images, text, or time series. The CGM has been evaluated on 13 datasets (6 standard datasets and 7 simulated) and compared to 14 recent generative models. It beats the state of the art in tabular data generation by a significant margin.