SAITS: Self-attention-based imputation for time series

2023/02/07 by Wenjie Du, David Côté, Yan Liu · 17 citations
Computer Science · Neuroscience · #Functional Brain Connectivity Studies #Machine Learning in Healthcare #Time Series Analysis and Forecasting

paper · doi:10.1016/j.eswa.2023.119619

openalex publication_date 2023/02/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30

Citations

• Bias and efficiency of multiple imputation compared with complete‐case analysis for missing covariate values
• Inference and missing data
• Missing Data Analysis: Making It Work in the Real World
• PhysioBank, PhysioToolkit, and PhysioNet

Cited by

• Beyond Observations: Reconstruction Error-Guided Irregularly Sampled Time Series Representation Learning
• Tackling Incomplete Data in Air Quality Prediction: A Bayesian Deep Learning Framework for Uncertainty Quantification
• Heterogeneous multivariate time series imputation by transformer model with missing position encoding
• Closing Gaps: An Imputation Analysis of ICU Vital Signs
• Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
• Glocal Information Bottleneck for Time Series Imputation
• Graph Mixing Additive Networks
• Revisiting Multivariate Time Series Forecasting with Missing Values
• Unlocking the Power of Mixture-of-Experts for Task-Aware Time Series Analytics
• SKY-Piano: A Multimodal Piano Performance Dataset
• Fourier Learning Machines: Nonharmonic Fourier-Based Neural Networks for Scientific Machine Learning
• STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systems
• Physics-informed deep operator network for traffic state estimation
• Masked Training for Robust Arrhythmia Detection from Digitalized Multiple Layout ECG Images
• ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation
• CS-SHRED: Enhancing SHRED for Robust Recovery of Spatiotemporal Dynamics
• MH-GIN: Multi-scale Heterogeneous Graph-based Imputation Network for AIS Data (Extended Version)