Tabular GAN-Based Oversampling of Imbalanced Time-to-Event Data for Survival Prediction

Class imbalance causes an underestimation (overestimation) of the hazard of minority class in survival prediction. A common strategy to handle class imbalance is to oversample the minority class by generating synthetic samples. This paper explores the potential of tabular Generative Adversarial Netw...

Full description

Saved in:
Bibliographic Details
Published in2023 8th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) pp. 376 - 380
Main Authors Tan, Huaning, Chen, Renxing, Qin, Meng, Tang, Lining, Wu, Zhibing, Luo, Qianlin, Quan, Yujuan
Format Conference Proceeding
LanguageEnglish
Published IEEE 26.04.2023
Subjects
Big Data
Class imbalance
Cloud computing
Generative adversarial networks
Hazards
Measurement
Oversampling
Predictive models
Survival Analysis
Tabular data generation
Training
Online AccessGet full text

Cover

More Information
Summary:Class imbalance causes an underestimation (overestimation) of the hazard of minority class in survival prediction. A common strategy to handle class imbalance is to oversample the minority class by generating synthetic samples. This paper explores the potential of tabular Generative Adversarial Networks (GANs) for oversampling based on real world survival datasets and simulated imbalanced datasets. We compare GAN-based oversampling methods with traditional methods on generation of minority instances and balanced survival prediction. Experimental results show that balanced survival prediction after GAN-based oversampling can outperforms baseline in some situations, and also demonstrate that traditional oversampling methods perform better than GAN-based methods on both minority samples generation and balanced survival prediction.
ISSN:2832-3734
DOI:10.1109/ICCCBDA56900.2023.10154883