ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Improved Recurrent Generative Adversarial Networks with Regularization Techniques and a Controllable Framework
Cited 11 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Minhyeok Lee, Donghyun Tae, Jae Hun Choi, Ho-Youl Jung, Junhee Seok
Issue Date
2020-10
Citation
Information Sciences, v.538, pp.428-443
ISSN
0020-0255
Publisher
Elsevier
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.1016/j.ins.2020.05.116
Abstract
Generative Adversarial Network (GAN), a deep learning framework to generate synthetic but realistic samples, has produced astonishing results for image synthesis. However, because GAN is routinely used for image datasets, regularization methods for GAN have been developed for convolutional layers. In this study, to expand these methods for time-series data, which are one of the most common data types in various real datasets, modified regularization methods are proposed for Long Short-Term Memory (LSTM)-based GANs. Specifically, the spectral normalization, hinge loss, orthogonal regularization, and the truncation trick are modified and assessed for LSTM-based GANs. Furthermore, a conditional GAN architecture called Controllable GAN (ControlGAN) is applied to LSTM-based GANs to produce the desired samples. The evaluations are conducted with sine wave data, air pollution datasets, and a medical time-series dataset obtained from intensive care units. As a result, ControlGAN with the spectral normalization on gates and cell states consistently outperforms the others, including the conventional model, called Recurrent Conditional GAN (RCGAN).
KSP Keywords
Air Pollution, Common data, Data type, Deep learning framework, Hinge loss, Intensive Care, Regularization method, Sine wave, Time series data, conventional model, deep learning(DL)