# Robustness Analysis of Deep Learning Models for Population Synthesis

arXiv: https://arxiv.org/abs/2211.13339 · HTML: https://mlsanity.com/paper/2211.13339/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 42 references that are in the map.
- First posted on arXiv 23 Nov 2022.

## Builds on (most cited first, 10 of 10)

- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Coupled Generative Adversarial Networks](https://mlsanity.com/paper/1606.07536/) (2016)
- [Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning](https://mlsanity.com/paper/1811.12808/) (2018)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [Prediction of rare feature combinations in population synthesis: Application of deep generative modelling](https://mlsanity.com/paper/1909.07689/) (2019)
- [Crossing Nets: Combining GANs and VAEs with a Shared Latent Space for Hand Pose Estimation](https://mlsanity.com/paper/1702.03431/) (2017)
- [Composite Travel Generative Adversarial Networks for Tabular and Sequential Population Synthesis](https://mlsanity.com/paper/2004.06838/) (2020)
- [DATGAN: Integrating expert knowledge into deep learning for synthetic tabular data](https://mlsanity.com/paper/2203.03489/) (2022)
- [Scalable Population Synthesis with Deep Generative Modeling](https://mlsanity.com/paper/1808.06910/) (2018)
- [A Probe Towards Understanding GAN and VAE Models](https://mlsanity.com/paper/1812.05676/) (2018)

## Built on by (most cited first, 1 of 1)

- [Feasible and Novel Synthetic Population Generation with Tabular and Sequential Travel Attributes](https://mlsanity.com/paper/2608.15867/) (2026)

## Abstract (arXiv)

Deep generative models have become useful for synthetic data generation, particularly population synthesis. The models implicitly learn the probability distribution of a dataset and can draw samples from a distribution. Several models have been proposed, but their performance is only tested on a single cross-sectional sample. The implementation of population synthesis on single datasets is seen as a drawback that needs further studies to explore the robustness of the models on multiple datasets. While comparing with the real data can increase trust and interpretability of the models, techniques to evaluate deep generative models' robustness for population synthesis remain underexplored. In this study, we present bootstrap confidence interval for the deep generative models, an approach that computes efficient confidence intervals for mean errors predictions to evaluate the robustness of the models to multiple datasets. Specifically, we adopt the tabular-based Composite Travel Generative Adversarial Network (CTGAN) and Variational Autoencoder (VAE), to estimate the distribution of the population, by generating agents that have tabular data using several samples over time from the same study area. The models are implemented on multiple travel diaries of Montreal Origin- Destination Survey of 2008, 2013, and 2018 and compare the predictive performance under varying sample sizes from multiple surveys. Results show that the predictive errors of CTGAN have narrower confidence intervals indicating its robustness to multiple datasets of the varying sample sizes when compared to VAE. Again, the evaluation of model robustness against varying sample size shows a minimal decrease in model performance with decrease in sample size. This study directly supports agent-based modelling by enabling finer synthetic generation of populations in a reliable environment.