Multivariate Time Series Imputation with Generative Adversarial Networks

By Yonghong Luo, Xiangrui Cai, Y. Zhang, Jun Xu, Xiaojie Yuan. Neural Information Processing Systems, 2018

534 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/0e984ccc4fbfc748836b2dde6fb1bdb5f9bf071a

How researchers see this paper

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

Citations in the corpus

Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models (2022, unknown): “This includes GAN-based approaches such as E2-GAN [34], and GRUI-GAN [33] or VAE-based approaches such as GP-VAE [15].”
A Survey on Deep Learning for Data-Driven Soft Sensors (2021, methodology): “For example, although VAE is the mainstream method to deal with missing value problems for soft sensor application using DL, methods based on RBM and GAN are also feasible in other ﬁelds [142], [143].”
CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation (2021, methodology): “Subsequent studies combined RNNs with other methods to improve imputation performance, such as GANs [9, 18, 19] and self-training [20].”
Latent ODEs for Irregularly-Sampled Time Series (2019, methodology): “Others have used a separate interpolation network [Shukla and Marlin, 2019], Gaussian processes [Futoma et al., 2017], or generative adversarial networks [Luo et al., 2018] to perform interpolation and imputation prior to running an RNN on time-discretized inputs.”
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2021, methodology): “utilized a GAN to infer missing time series data [176].”
Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, background): “Recent years, imputation methods have been greatly for both deterministic imputation [23, 27, 154] and probabilistic imputation [65], including diffusion-based approaches.”
Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting (2020, background): “A majority of such studies [16, 10, 8, 17, 18, 19, 20] rely on LSTM or GRU to model the temporal dynamics in the time series data.”
SAITS: Self-Attention-based Imputation for Time Series (2022, methodology): “Among them, the methods [21, 30, 32, 33] are autoregressive models that are highly susceptible to compounding errors [42, 31].”
Generative Adversarial Networks: A Survey and Taxonomy (2019, background): “GANs have been applied to some other ﬁelds, (e.g., time series generation [20], [21], [103] and natural language processing [15], [104]–[106]) with some success.”
GP-VAE: Deep Probabilistic Time Series Imputation (2019, methodology): “To the best of our knowledge, the only deep generative model for missing value imputation that does account for the time series nature of the data is the GRUI-GAN [34], which we describe in Sec.”
Generative Adversarial Networks in Time Series: A Systematic Literature Review (2022, unknown): “Time series Imputation/Repairing MTS-GAN [42] CNN-CNN [84] DCGAN variant [43] AE-GRUI [71] RGAN [92] FCN-FCN [15] GRUI-GRUI [70] TEP, Point Machine, Wind Turbin data, PeMS, PhysioNet Challenge 2012, KDD CUP 2018, Parking lot data, Visually, MMD, MAE, MSE, RMSE, MRE, Spatial Similarity, AUC score”