Composite Travel Generative Adversarial Networks for Tabular and Sequential Population Synthesis

Badu-Marfo, Godwin; Farooq, Bilal; Paterson, Zachary

doi:10.48550/arxiv.2004.06838

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They show that this new model was statistically better than IPF techniques, Gibbs sampling, and the VAE of Borysov et al (2019). Finally, Badu-Marfo et al (2020) created a new GAN named Composite Travel GAN (CTGAN). Their GAN is based on the Coupled GAN (CoGAN) (Liu and Tuzel, 2016) and is used to generate the table of attributes for the population and the sequence of Origin-Destination segments.…”

Section: Noisementioning

confidence: 99%

See 1 more Smart Citation

DATGAN: Integrating expert knowledge into deep learning for synthetic tabular data

Lederrey¹,

Hillel²,

Bierlaire³

2022

Preprint

View full text Add to dashboard Cite

Synthetic data can be used in various applications, such as correcting bias datasets or replacing scarce original data for simulation purposes. Generative Adversarial Networks (GANs) are considered stateof-the-art for developing generative models. However, these deep learning models are data-driven, and it is, thus, difficult to control the generation process. It can, therefore, lead to the following issues: lack of representativity in the generated data, the introduction of bias, and the possibility of overfitting the sample's noise. This article presents the Directed Acyclic Tabular GAN (DATGAN) to address these limitations by integrating expert knowledge in deep learning models for synthetic tabular data generation. This approach allows the interactions between variables to be specified explicitly using a Directed Acyclic Graph (DAG). The DAG is then converted to a network of modified Long Short-Term Memory (LSTM) cells to accept multiple inputs. Multiple DATGAN versions are systematically tested on multiple assessment metrics. We show that the best versions of the DATGAN outperform state-of-the-art generative models on multiple case studies. Finally, we show how the DAG can create hypothetical synthetic datasets.

show abstract

Section: Noisementioning

confidence: 99%

“…For the statistical tests, we build on existing approaches in the transportation literature (Garrido et al, 2019;Borysov et al, 2019;Badu-Marfo et al, 2020). The idea is to compute frequency lists (i.e.…”

Section: Statistical Testsmentioning

confidence: 99%