English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Synthetic data can be used in various applications, such as correcting biasdatasets or replacing scarce original data for simulation purposes. GenerativeAdversarial Networks (GANs) are considered state-of-the-art for developinggenerative models. However, these deep learning models are data-driven, and itis, thus, difficult to control the generation process. It can, therefore, leadto the following issues: lack of representativity in the generated data, theintroduction of bias, and the possibility of overfitting the sample's noise.This article presents the Directed Acyclic Tabular GAN (DATGAN) to addressthese limitations by integrating expert knowledge in deep learning models forsynthetic tabular data generation. This approach allows the interactionsbetween variables to be specified explicitly using a Directed Acyclic Graph(DAG). The DAG is then converted to a network of modified Long Short-TermMemory (LSTM) cells to accept multiple inputs. Multiple DATGAN versions aresystematically tested on multiple assessment metrics. We show that the bestversions of the DATGAN outperform state-of-the-art generative models onmultiple case studies. Finally, we show how the DAG can create hypotheticalsynthetic datasets.

DATGAN: Integrating expert knowledge into deep learning for synthetic tabular data