Generative Oversampling with a Contrastive Variational Autoencoder
© 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 t...
Main Authors: | Dai, Wangzhi (Author), Ng, Kenney (Author), Severson, Kristen A (Author), Huang, Wei (Author), Anderson, Fred (Author), Stultz, Collin M (Author) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor), Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), MIT-IBM Watson AI Lab (Contributor), Massachusetts Institute of Technology. Institute for Medical Engineering & Science (Contributor) |
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers (IEEE),
2022-01-04T15:05:25Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Generative Oversampling with a Contrastive Variational Autoencoder
by: Dai, Wangzhi, et al.
Published: (2021) -
Identifying unreliable predictions in clinical risk models
by: Paul D. Myers, et al.
Published: (2020-01-01) -
Generating functional protein variants with variational autoencoders.
by: Alex Hawkins-Hooker, et al.
Published: (2021-02-01) -
Latent Space Expanded Variational Autoencoder for Sentence Generation
by: Tianbao Song, et al.
Published: (2019-01-01) -
Junction tree variational autoencoder for molecular graph generation
by: Jin, Wengong, et al.
Published: (2021)