[1811.11264] Synthesizing Tabular Data using Generative Adversarial Networks

Generative adversarial networks (GANs) implicitly learn the probability distribution of a dataset and can draw samples from the distribution. This paper presents, Tabular GAN (TGAN), a generative adversarial network which can generate tabular data like medical or educational records. Using the power of deep neural networks, TGAN generates high-quality and fully synthetic tables while simultaneously generating discrete and continuous variables. When we evaluate our model on three datasets, we find that TGAN outperforms conventional statistical generative models in both capturing the correlation between columns and scaling up for large datasets.

1 mentions: @upura0
Date: 2019/08/18 11:16

Referring Tweets

@upura0 TGANの論文読んだけど、名状しがたい「ふむ……」感があるな t.co/ixU4cez76n

Related Entries

Read more [2001.05166] ShapeVis: High-dimensional Data Visualization at Scalecontact arXivarXiv Twitter
0 users, 2 mentions 2020/01/17 02:20
Read more [2001.10054] StageNet: Stage-Aware Neural Networks for Health Risk Predictioncontact arXivarXiv Twit...
0 users, 4 mentions 2020/01/30 03:51
Read more [2002.06910] t-viSNE: Interactive Assessment and Interpretation of t-SNE Projectionscontact arXivarX...
0 users, 2 mentions 2020/02/19 03:50
Read more [2003.00201] What Emotions Make One or Five Stars? Understanding Ratings of Online Product Reviews b...
0 users, 2 mentions 2020/03/04 05:21
Read more [1811.00770] A Survey on Natural Language Processing for Fake News Detectioncontact arXivarXiv Twitt...
0 users, 3 mentions 2020/03/07 03:51