ProcessGAN: Generating Privacy-Preserving Time-Aware Process Data with Conditional Generative Adversarial Nets
ACM Transactions on Knowledge Discovery from Data · 2024-11-30 · 18 (9) · 1-31
DOI: 10.1145/3687464 ↗At a glance
Journal article in ACM Transactions on Knowledge Discovery from Data, published online on 2024-11-12. Written by Keyi Li and 4 co-authors. Institution: Electrical and Computer Engineering Department, Rutgers University, New Brunswick, New Jersey, USA. Cited 8 times so far (Crossref); 50 references. The full text is freely available (open access, CC BY 4.0). Funded by: NLM NIH HHS, U.S. National Institutes of Health/National Library of Medicine.
Abstract (original language)
Process data constructed from event logs provides valuable insights into procedural dynamics over time. The confidential information in process data, together with the data’s intricate nature, makes the datasets not sharable and challenging to collect. Consequently, research is limited using process data and analytics in the process mining domain. In this study, we introduced a synthetic process data generation task to address the limitation of sharable process data. We introduced a generative adversarial network, called ProcessGAN, to generate process data with activity sequences and corresponding timestamps. ProcessGAN consists of a transformer-based network as the generator, and a time-aware self-attention network as the discriminator. It can generate privacy-preserving process data from random noise. ProcessGAN considers the duration of the process and time intervals between activities to generate realistic activity sequences with timestamps. We evaluated ProcessGAN on five real-world datasets, two that are public and three collected in medical domains that are private. To evaluate the synthetic data, in addition to statistical metrics, we trained a supervised model to score the synthetic processes. We also used process mining to discover workflows for synthetic medical processes and had domain experts evaluate the clinical applicability of the synthetic workflows. ProcessGAN outperformed the existing generative models in generating complex processes with valid parallel pathways. The synthetic process data generated by ProcessGAN better represented the long-range dependencies between activities, a feature relevant to complicated medical and other processes. The timestamps generated by the ProcessGAN model showed similar distributions with the authentic timestamps. In addition, we trained a transformer-based network to generate synthetic contexts (e.g., patient demographics) that were associated with the synthetic processes. The synthetic contexts generated by our model outperformed the baseline models, with the distributions similar to the authentic contexts. We conclude that ProcessGAN can generate sharable synthetic process data indistinguishable from authentic data. Our source code is available in https://github.com/raaachli/ProcessGAN .
Subjects
Author keywords
Authors and institutions
- Electrical and Computer Engineering Department, Rutgers University, New Brunswick, New Jersey, USA.
- Waymo, Mountain View, CA, USA.
- Children's National Hospital, Washington, DC, USA.
- Electrical and Computer Engineering Department, Rutgers University, New Brunswick, NJ, USA.
ORCID profiles: Keyi Li, Sen Yang, Travis M Sullivan, Randall S Burd, Ivan Marsic
Funding
- NLM NIH HHS
- U.S. National Institutes of Health/National Library of Medicine
Cite
APA
Li, K., Yang, S., Sullivan, T. M., Burd, R. S., & Marsic, I. (2024). ProcessGAN: Generating Privacy-Preserving Time-Aware Process Data with Conditional Generative Adversarial Nets. ACM Transactions on Knowledge Discovery from Data, 18(9), 1-31. https://doi.org/10.1145/3687464
Vancouver
Li K, Yang S, Sullivan TM, Burd RS, Marsic I. ProcessGAN: Generating Privacy-Preserving Time-Aware Process Data with Conditional Generative Adversarial Nets. ACM Transactions on Knowledge Discovery from Data. 2024;18(9):1-31. doi:10.1145/3687464
BibTeX
@article{Li2024,
author = {Li, Keyi and Yang, Sen and Sullivan, Travis M and Burd, Randall S and Marsic, Ivan},
title = {ProcessGAN: Generating Privacy-Preserving Time-Aware Process Data with Conditional Generative Adversarial Nets},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2024},
volume = {18},
number = {9},
pages = {1--31},
doi = {10.1145/3687464}
}
EUVIMED