GAN Baseline

GAN baselines are foundational models used to evaluate the performance of newer generative adversarial networks (GANs) across diverse data types, including images and tabular data. Current research focuses on improving GAN baselines by addressing limitations such as mode collapse, preserving contextual correlations in tabular data, and enhancing the quality and utility of synthetic data while maintaining privacy. These improvements are crucial for advancing data synthesis techniques, enabling responsible data sharing in various fields like medicine and statistics, and facilitating more robust and reliable machine learning applications.

Papers

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 Tabular Generative Adversarial Network GAN Baseline

May 27, 2024

May 23, 2024

Neuroexplicit Diffusion Models for Inpainting of Optical Flow Fields
Tom Fischer, Pascal Peter, Joachim Weickert, Eddy Ilg
Deep Learning Convolutional Neural Network Diffusion Probabilistic Model Neural Diffusion GAN Baseline Optical Flow Field

April 15, 2024

Multi-objective evolutionary GAN for tabular data synthesis
Nian Ran, Bahrul Ilmi Nasution, Claire Little, Richard Allmendinger, Mark Elliot
Generative Adversarial Network Synthetic Data Tabular Data Synthesis GAN Baseline

August 15, 2023

Method for Generating Synthetic Data Combining Chest Radiography Images with Tabular Clinical Information Using Dual Generative Models
Tomohiro Kikuchi, Shouhei Hanaoka, Takahiro Nakao, Tomomi Takenaga, Yukihiro Nomura, Harushi Mori, Takeharu Yoshikawa
Generative Adversarial Network Practical Method Tabular Data Box Embeddings Synthetic Electronic Health Record GAN Baseline Synthetic Chest X Ray

July 1, 2023

CasTGAN: Cascaded Generative Adversarial Network for Realistic Tabular Data Synthesis
Abdallah Alshantti, Damiano Varagnolo, Adil Rasheed, Aria Rahmati, Frank Westad
Generative Adversarial Network Synthetic Data Adversarial Learning Synthetic Tabular Data Tabular Data Synthesis GAN Baseline

November 17, 2022

Permutation-Invariant Tabular Data Synthesis
Yujin Zhu, Zilong Zhao, Robert Birke, Lydia Y. Chen
Synthetic Data Synthetic Tabular Data Tabular Data Synthesis GAN Baseline

August 25, 2022

Combating Mode Collapse in GANs via Manifold Entropy Estimation
Haozhe Liu, Bing Li, Haoqian Wu, Hanbang Liang, Yawen Huang, Yuexiang Li, Bernard Ghanem, Yefeng Zheng
Generative Adversarial Network Mode Collapse GAN Baseline

June 5, 2022

Diffusion-GAN: Training GANs with Diffusion
Zhendong Wang, Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou
Generative Adversarial Network Diffusion Explainer Diffusion GAN GAN Baseline GAN Framework

April 19, 2022

Imbalanced Classification via a Tabular Translation GAN
Jonathan Gradstein, Moshe Salhov, Yoav Tulpan, Ofir Lindenbaum, Amir Averbuch
Generative Adversarial Network Class Imbalance Imbalanced Datasets Imbalanced Classification Regularization Loss Minority Sample GAN Baseline

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