Generating Privacy-Preserving Longitudinal Synthetic Data

Abstract

Before synthetic data (SD) generators are able to generate entire electronic health records, many challenges still have to be tackled. One of these challenges is to generate both privacy-preserving and longitudinal SD. This research combines the research streams of longitudinal SD and privacy-preserving static SD and presents a novel GAN architecture called Time-ADS-GAN. Time-ADS-GAN outperforms current state-of-the-art models on both utility and privacy on three datasets and is able to reproduce the results of a healthcare study significantly better than TimeGAN. As a second contribution, a variation of the $\epsilon$-identifiability metric is introduced and used in the analysis.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

van Hoorn et al. "Generating Privacy-Preserving Longitudinal Synthetic Data." NeurIPS 2023 Workshops: SyntheticData4ML, 2023.

Markdown

[van Hoorn et al. "Generating Privacy-Preserving Longitudinal Synthetic Data." NeurIPS 2023 Workshops: SyntheticData4ML, 2023.](https://mlanthology.org/neuripsw/2023/vanhoorn2023neuripsw-generating/)

BibTeX

@inproceedings{vanhoorn2023neuripsw-generating,
  title     = {{Generating Privacy-Preserving Longitudinal Synthetic Data}},
  author    = {van Hoorn, Robin and Bakkes, Tom and Tokoutsi, Zoi and de Jong, Ymke and Bouwman, R. Arthur and Pechenizkiy, Mykola},
  booktitle = {NeurIPS 2023 Workshops: SyntheticData4ML},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/vanhoorn2023neuripsw-generating/}
}