Time-series Generative Adversarial Networks

By Jinsung Yoon, Daniel Jarrett, Mihaela van der Schaar. Neural Information Processing Systems, 2019

1,481 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Generative Adversarial Networks in Time Series: A Systematic Literature Review (2022, methodology): “In terms of qualitatively evaluating time series based GANs, it normally conducts t-SNE [95] and PCA [13] analyses to visualize how well the generated distributions resemble the original distributions [107].”
Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, methodology): “GANs mainly consist of two models: a generator 𝐺 and a discriminator 𝐷 .”
Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting (2021, methodology): “In the multivariate setting we also have point forecasting meth-ods (Lai et al., 2018; Li et al., 2019) as well as probabilistic methods, like this method, which explicitly model the data distribution using Gaussian copulas (Salinas et al., 2019a), GANs (Yoon et al., 2019), or normalizing ﬂows (de B”
UvA-DARE (Digital Academic Repository) Neural Relational Inference for Interacting Systems Neural Relational Inference for Interacting Systems (2018, unknown): “For GAN-like models, (Yoon et al., 2019) combine adversarial training and a supervised learning objective for time series forecasting.”
Data Augmentation techniques in time series domain: a survey and taxonomy (2022, methodology): “Regarding the previous models, this architecture is able to outperform previous models such as TimeGAN providing better synthetic data for DA.”