Generating survey databases with Wasserstein Generative Adversarial Networks

Generative adversarial network; Sampling weights; Support vector data description; Synthetic data set; Wasserstein distance; Wasserstein generative adversarial network; Adversarial networks; Anonymization; Sampling weight; Survey data; Synthetic database; Synthetic datasets; Artificial Intelligence

Abstract :

[en] In a world increasingly surrounded by data, data privacy and anonymization are becoming more and more important. Under these circumstances, the need for synthetic databases that replicate the characteristics of the population while preserving privacy is arising. In this article, we investigate how we can use Wasserstein Generative Adversarial Networks (WGANs), developed by Arjovsky et al. [1] in the context of image generation, to create synthetic survey databases. Survey data have both categorical and continuous variables and especially contain sampling weights that will be introduced in the proposed procedures. We evaluate the quality of the (generated) synthetic data through different indicators and especially a new practical and intuitive measure based on Support Vector Data Description (SVDD). All our analyses are achieved with the Labour Force Survey (LFS) data for Belgium.

Disciplines :

Engineering, computing & technology: Multidisciplinary, general & others

Author, co-author :

Annoye, Hugues ; CAPE, UCLouvain Saint-Louis Bruxelles, Brussels, Belgium ; ISBA, Université Catholique de Louvain, Louvain-la-Neuve, Belgium

Heuchenne, Cédric ; Université de Liège - ULiège > HEC Liège : UER > UER Opérations : Statistique appliquée à la gestion et à l'économie ; CAPE, UCLouvain Saint-Louis Bruxelles, Brussels, Belgium ; ISBA, Université Catholique de Louvain, Louvain-la-Neuve, Belgium

Language :

English

Title :

Generating survey databases with Wasserstein Generative Adversarial Networks

Publication date :

November 2025

Journal title :

Applied Intelligence

ISSN :

0924-669X

eISSN :

1573-7497

Publisher :

Springer

Volume :

Issue :

Peer reviewed :

Peer Reviewed verified by ORBi

Additional URL :

https://link.springer.com/content/pdf/10.1007/s10489-025-06871-x.pdf

Funders :

ERDF - European Regional Development Fund

Funding text :

This work was partially funded by European Regional Development Fund (ERDF, project 2021BE16RFPR001-T-11-05).

Available on ORBi :

since 23 January 2026

Statistics

Number of views

6 (0 by ULiège)

Number of downloads

0 (0 by ULiège)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenCitations

OpenAlex citations

Bibliography

Arjovsky M, Chintala S, Bottou L (2017) Wasserstein generative adversarial networks. In: International conference on machine learning, pp 214–223. PMLR
I. Goodfellow J. Pouget-Abadie M. Mirza B. Xu D. Warde-Farley S. Ozair A. Courville Y. Bengio Generative adversarial networks Commun ACM 63 11 139 144 4173633 10.1145/3422622
Kingma DP, Welling M (2022) Auto-encoding variational bayes. arXiv:1312.6114 [stat.ML]
Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Advances in neural information processing systems, vol 33, pp 6840–6851
Kotelnikov A, Baranchuk D, Rubachev I, Babenko A (2023) Tabddpm: modelling tabular data with diffusion models. In: International conference on machine learning, pp 17564–17579. PMLR
Annoye H, Beretta A, Heuchenne C (2024) Statistical matching using kernel canonical correlation analysis and super-organizing map. Expert Syst Appl 123134. https://doi.org/10.1016/j.eswa.2023.123134
Cheng J, Yang Y, Tang X, Xiong N, Zhang Y, Lei F (2020) Generative adversarial networks: a literature review. KSII Trans Internet Inf Syst 14(12)
Xu L, Veeramachaneni K (2018) Synthesizing tabular data using generative adversarial networks. arXiv:1811.11264 [cs.LG]
Camino R, Hammerschmidt C, State R (2018) Generating multi-categorical samples with generative adversarial networks. arXiv:1807.01202 [stat.ML]
Walia M, Tierney B, McKeever S (2020) Synthesising tabular data using Wasserstein conditional gans with gradient penalty (wcgan-gp). In: AICS, pp 325–336
Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville A (2017) Improved training of Wasserstein gans. Advances in neural information processing systems, vol 30
A. Borji Pros and cons of gan evaluation measures Comput Vis Image Underst 179 41 65 10.1016/j.cviu.2018.10.009
A. Borji Pros and cons of gan evaluation measures: new developments Comput Vis Image Underst 215 103329 10.1016/j.cviu.2021.103329
Schuhmacher D, Bähre B, Gottschlich C, Hartmann V, Heinemann F, Schmitzer B (2024) transport: computation of optimal transport plans and Wasserstein distances. R package version 0.15-0. https://cran.r-project.org/package=transport
Lu S, Yu L, Feng S, Zhu Y, Zhang W (2019) Cot: cooperative training for generative modeling of discrete data. In: International conference on machine learning, pp 4164–4172. PMLR
Fang J, Li A, Jiang Q (2019) Gdagan: an anonymization method for graph data publishing using generative adversarial network. In: 2019 6th International Conference on Information Science and Control Engineering (ICISCE), pp 309–313. IEEE
Feutry C, Piantanida P, Bengio Y, Duhamel P (2018) Learning anonymized representations with adversarial neural networks. arXiv:1802.09386 [stat.ML]
Bae H, Jung D, Choi H-S, Yoon S (2019) Anomigan: generative adversarial networks for anonymizing private medical data. In: Pacific symposium on biocomuting 2020, pp 563–574. World Scientific
Park N, Mohammadi M, Gorde K, Jajodia S, Park H, Kim Y (2018) Data synthesis based on generative adversarial networks. Proceedings of the VLDB endowment, vol 11, no 10, pp 1071–1083 https://doi.org/10.14778/3231751.3231757
J. Engelmann S. Lessmann Conditional Wasserstein gan-based oversampling of tabular data for imbalanced learning Expert Syst Appl 174 114582 10.1016/j.eswa.2021.114582
Xu L, Skoularidou M, Cuesta-Infante A, Veeramachaneni K (2019) Modeling tabular data using conditional gan. Advances in neural information processing systems, vol 32
Vega-Márquez B, Rubio-Escudero C, Riquelme JC, Nepomuceno-Chamorro I (2020) Creation of synthetic data with conditional generative adversarial networks. In: Martínez Álvarez F, Troncoso Lora A, Sáez Muñoz JA, Quintián H, Corchado E (eds) 14th International conference on soft computing models in industrial and environmental applications (SOCO 2019), pp 231–240. Springer, Cham
Metz L, Poole B, Pfau D, Sohl-Dickstein J (2017) Unrolled generative adversarial networks. arXiv:1611.02163 [cs.LG]
Zhang Z, Li M, Yu J (2018) On the convergence and mode collapse of gan. In: SIGGRAPH Asia 2018 technical briefs, pp 1–4
Villani C (2009) Optimal transport: old and new. Grundlehren der mathematischen Wissenschaften a series of comprehensive studies in mathematics, vol 338. Springer, Heidelberg
Kingma DP, Ba J (2017) Adam: a method for stochastic optimization. arXiv:1412.6980 [cs.LG]
Maas AL, Hannun AY, Ng AY-T et al (2013) Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the international conference on machine learning, vol 30, p 3. Atlanta, GA
Jamotton C, Hainaut D (2024) Variational autoencoder for synthetic insurance data. Intell Syst Appl 24:200455. https://doi.org/10.1016/j.iswa.2024.200455
Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: International conference on machine learning, pp 1310–1318. Pmlr
Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, vol 30
Naeem MF, Oh SJ, Uh Y, Choi Y, Yoo J (2020) Reliable fidelity and diversity metrics for generative models. In: International conference on machine learning, pp 7176–7185. PMLR
Kynkäänniemi T, Karras T, Laine S, Lehtinen J, Aila T (2019) Improved precision and recall metric for assessing generative models. Advances in neural information processing systems, vol 32
Boltz S, Debreuve E, Barlaud M (2007) knn-based high-dimensional Kullback-Leibler distance for tracking. In: Eighth international Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS’07), pp 16–16. IEEE
D.M.J. Tax R.P.W. Duin Support vector data description Mach Learn 54 45 66 10.1023/B:MACH.0000008084.60811.49
B. Schölkopf J.C. Platt J. Shawe-Taylor A.J. Smola R.C. Williamson Estimating the support of a high-dimensional distribution Neural Comput 13 7 1443 1471 10.1162/089976601750264965
C.H. Lampert et al. Kernel methods in computer vision Found Trends® Comput Graph Vision 4 3 193 285 2974118 10.1561/0600000027
M.K. Baowaly C.-C. Lin C.-L. Liu K.-T. Chen Synthesizing electronic health records using improved generative adversarial networks J Am Med Inform Assoc 26 3 228 241 10.1093/jamia/ocy142
Bellemare MG, Danihelka I, Dabney W, Mohamed S, Lakshminarayanan B, Hoyer S, Munos R (2017) The cramer distance as a solution to biased Wasserstein gradients. arXiv:1705.10743 [cs.LG]
Mottini A, Lheritier A, Acuna-Agost R (2018) Airline passenger name record generation using generative adversarial networks. arXiv:1807.06657 [cs.LG]
Xie L, Lin K, Wang S, Wang F, Zhou J (2018) Differentially private generative adversarial network. arXiv:1802.06739
E. Liu Z. Chu X. Zhang Wasserstein gan for moving differential privacy protection Sci Rep 15 1 19634 10.1038/s41598-025-03178-2
D.C. Dowson B.V. Landau The fréchet distance between multivariate normal distributions J Multivar Anal 12 3 450 455 10.1016/0047-259X(82)90077-X