DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Beomsoo | ko |
dc.contributor.author | Choi, Jang-Ho | ko |
dc.contributor.author | Choo, Jaegul | ko |
dc.date.accessioned | 2022-01-14T06:53:47Z | - |
dc.date.available | 2022-01-14T06:53:47Z | - |
dc.date.created | 2021-12-03 | - |
dc.date.issued | 2021-11-17 | - |
dc.identifier.citation | The 13th Asian Conference on Machine Learning, ACML 2021 | - |
dc.identifier.uri | http://hdl.handle.net/10203/291807 | - |
dc.description.abstract | Success of training deep learning models largely depends on the amount and quality of training data. Although numerous data augmentation techniques have already been pro- posed for certain domains such as computer vision where simple schemes such as rotation and flipping have been shown to be effective, other domains such as time-series data have a relatively smaller set of augmentation techniques readily available. Besides, data imbalance is a phenomenon that is often observed in real-world data. However, a simple oversampling may make a model vulnerable to overfitting, so a proper data augmentation is desired. To tackle these problems, we propose a data augmentation method that utilizes latent vectors of an autoencoder in a novel way. When input data is perturbed in its latent space, the reconstructed input data retains similar properties to the original one. On the other hand, adversarial augmentation is a technique to train robust deep neural networks against un- foreseen data shifts or corruptions by providing a downstream model with difficult samples to predict. Our method adversarily perturbs input data in its latent space so that the aug- mented data is diverse and conducive to reducing test error of a downstream model. The experimental results demonstrate that our method achieves a right balance in significantly modifying the input data to help generalization while keeping the realism of it. | - |
dc.language | English | - |
dc.publisher | ACML | - |
dc.title | Augmenting Imbalanced Time-series Data via Adversarial Perturbation in Latent Space | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | The 13th Asian Conference on Machine Learning, ACML 2021 | - |
dc.identifier.conferencecountry | TH | - |
dc.identifier.conferencelocation | Virtual | - |
dc.contributor.localauthor | Choo, Jaegul | - |
dc.contributor.nonIdAuthor | Kim, Beomsoo | - |
dc.contributor.nonIdAuthor | Choi, Jang-Ho | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.