CTAB-GAN+: enhancing tabular data synthesis
Frontiers in Big Data · 08.01.2024 · 6
DOI: 10.3389/fdata.2023.1296508 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Big Data, online erschienen am 08.01.2024. Verfasst von Zilong Zhao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, Netherlands. Die Arbeit wurde bisher 124-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The usage of synthetic data is gaining momentum in part due to the unavailability of original data due to privacy and legal considerations and in part due to its utility as an augmentation to the authentic data. Generative adversarial networks (GANs), a paragon of generative models, initially for images and subsequently for tabular data, has contributed many of the state-of-the-art synthesizers. As GANs improve, the synthesized data increasingly resemble the real data risking to leak privacy. Differential privacy (DP) provides theoretical guarantees on privacy loss but degrades data utility. Striking the best trade-off remains yet a challenging research question. In this study, we propose CTAB-GAN+ a novel conditional tabular GAN. CTAB-GAN+ improves upon state-of-the-art by (i) adding downstream losses to conditional GAN for higher utility synthetic data in both classification and regression domains; (ii) using Wasserstein loss with gradient penalty for better training convergence; (iii) introducing novel encoders targeting mixed continuous-categorical variables and variables with unbalanced or skewed data; and (iv) training with DP stochastic gradient descent to impose strict privacy guarantees. We extensively evaluate CTAB-GAN+ on statistical similarity and machine learning utility against state-of-the-art tabular GANs. The results show that CTAB-GAN+ synthesizes privacy-preserving data with at least 21.9% higher machine learning utility (i.e., F1-Score) across multiple datasets and learning tasks under given privacy budget.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, Netherlands.
- Technical University of Munich School of Social Sciences and Technology, Technical University of Munich, Munich, Germany.
- Computer Science Department, University of Turin, Turin, Italy.
- AEGON, The Hague, Netherlands.
- Computer Science Department, University of Neuchâtel, Neuchâtel, Switzerland.
Zitieren
APA
Zhao, Z., Kunar, A., Birke, R., Van der Scheer, H., & Chen, L. Y. (2024). CTAB-GAN+: enhancing tabular data synthesis. Frontiers in Big Data, 6. https://doi.org/10.3389/fdata.2023.1296508
Vancouver
Zhao Z, Kunar A, Birke R, Van der Scheer H, Chen LY. CTAB-GAN+: enhancing tabular data synthesis. Frontiers in Big Data. 2024;6. doi:10.3389/fdata.2023.1296508
BibTeX
@article{Zhao2024,
author = {Zhao, Zilong and Kunar, Aditya and Birke, Robert and Van der Scheer, Hiek and Chen, Lydia Y},
title = {CTAB-GAN+: enhancing tabular data synthesis},
journal = {Frontiers in Big Data},
year = {2024},
volume = {6},
doi = {10.3389/fdata.2023.1296508}
}
EUVIMED