Tabular Generative Adversarial Network

Tabular Generative Adversarial Networks (Tabular GANs) aim to create realistic synthetic tabular datasets, addressing needs in data augmentation, privacy-preserving data sharing, and software testing. Research currently focuses on improving the quality and efficiency of these synthetic datasets, particularly by enhancing the ability of GAN architectures like CTGAN and its variants to capture complex relationships and contextual information within the data, while mitigating privacy risks associated with data leakage. This field is significant because high-quality synthetic data can enable data analysis and machine learning in situations where real data is scarce, sensitive, or otherwise unavailable, impacting various domains from healthcare to finance.

Papers

October 2, 2024

TAEGAN: Generating Synthetic Tabular Data For Data Augmentation
Jiayu Li, Zilong Zhao, Kevin Yee, Uzair Javaid, Biplab Sikdar
Data Augmentation Tabular Data Synthetic Tabular Data Tabular Deep Learning Synthetic Tabular Data Generation Tabular Generative Adversarial Network

September 3, 2024

CTG-KrEW: Generating Synthetic Structured Contextually Correlated Content by Conditional Tabular GAN with K-Means Clustering and Efficient Word Embedding
Riya Samanta, Bidyut Saha, Soumya K. Ghosh, Sajal K. Das
High Efficiency K Mean Synthetic Tabular Data GAN Baseline Tabular Generative Adversarial Network

March 31, 2024

Privacy Re-identification Attacks on Tabular GANs
Abdallah Alshantti, Adil Rasheed, Frank Westad
Generative Model Generative Adversarial Network Synthetic Data Generative Modeling Tabular Generative Adversarial Network Identification Attack

January 3, 2024

Adversarial Machine Learning-Enabled Anonymization of OpenWiFi Data
Samhita Kuili, Kareem Dabbour, Irtiza Hasan, Andrea Herscovich, Burak Kantarci, Marcel Chenier, Melike Erol-Kantarci
Generative Adversarial Network Synthetic Data Adversarial Learning Consistent Anonymization Effect Tabular Generative Adversarial Network

October 18, 2023

Black-Box Training Data Identification in GANs via Detector Networks
Lukman Olagoke, Salil Vadhan, Seth Neel
Generative Adversarial Network GAN Model Detection Network Tabular Generative Adversarial Network

October 10, 2023

An improved CTGAN for data processing method of imbalanced disk failure
Jingbo Jia, Peng Wu, Hussain Dawood
Adversarial Learning Data Imbalance Data Preprocessing Tabular Generative Adversarial Network Disk Failure

February 3, 2023

GTV: Generating Tabular Data via Vertical Federated Learning
Zilong Zhao, Han Wu, Aad Van Moorsel, Lydia Y. Chen
Generative Adversarial Network Tabular Data Vertical Federated Learning Tabular Generative Adversarial Network Centralized Stochastic Gradient Descent

November 14, 2022

Row Conditional-TGAN for generating synthetic relational databases
Mohamed Gueye, Yazid Attabi, Maxime Dumas
Generative Adversarial Network Tabular Generative Adversarial Network Synthetic Relational

October 5, 2022

ciDATGAN: Conditional Inputs for Tabular GANs
Gael Lederrey, Tim Hillel, Michel Bierlaire
Generative Adversarial Network Cycle GAN Tabular Generative Adversarial Network Partial Input

April 1, 2022

CTAB-GAN+: Enhancing Tabular Data Synthesis
Zilong Zhao, Aditya Kunar, Robert Birke, Lydia Y. Chen
Generative Adversarial Network GAN Model C Gan Tabular Data Synthesis Tabular Generative Adversarial Network GAN Baseline

December 16, 2021

Imbalanced Sample Generation and Evaluation for Power System Transient Stability Using CTGAN
Gengshi Han, Shunyu Liu, Kaixuan Chen, Na Yu, Zunlei Feng, Mingli Song
Global Evaluation Conditional Generation Imbalanced Dataset Tabular Generative Adversarial Network Transient Stability

December 3, 2021

Generative Adversarial Networks for Synthetic Data Generation: A Comparative Study
Claire Little, Mark Elliot, Richard Allmendinger, Sahel Shariati Samani
Generative Adversarial Network Comparative Study Synthetic Data Generation Data Synthesis Tabular Generative Adversarial Network Synthetic Census