Generative Oversampling with a Contrastive Variational Autoencoder
| Autor: | Collin M. Stultz, Frederick A. Anderson, Kenney Ng, Kristen A. Severson, Wangzhi Dai, Wei Huang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
0303 health sciences
business.industry Computer science 02 engineering and technology Machine learning computer.software_genre Autoencoder 03 medical and health sciences Generative model 0202 electrical engineering electronic engineering information engineering Oversampling 020201 artificial intelligence & image processing Artificial intelligence business computer Generative grammar 030304 developmental biology |
| Zdroj: | Other repository ICDM |
| Popis: | © 2019 IEEE. Although oversampling methods are widely used to deal with class imbalance problems, most only utilize observed samples in the minority class and ignore the rich information available in the majority class. In this work, we use an oversampling method that leverages information in both the majority and minority classes to mitigate the class imbalance problem. Experimental results on two clinical datasets with highly imbalanced outcomes demonstrate that prediction models can be significantly improved using data obtained from this oversampling method when the number of minority class samples is very small. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|