Research map / Time series / Causal and generative time series
Generative Semi-supervised Learning for Multivariate Time Series Imputation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use SSGAN instead of the strongest baseline at each missing rate | time-series imputation · Activity | RMSE: 0.621 -> 0.600; 0.686 -> 0.666; 0.786 -> 0.759; 0.836 -> 0.803; 0.867 -> 0.841 | Helped |
| Use SSGAN instead of the strongest baseline at each missing rate | time-series imputation · PhysioNet | RMSE: 0.611 -> 0.598; 0.672 -> 0.670; 0.779 -> 0.762; 0.809 -> 0.782; 0.850 -> 0.818 | Helped |
| Use SSGAN instead of the strongest baseline at each missing rate | time-series imputation · KDD | RMSE: 0.522 -> 0.435; 0.562 -> 0.461; 0.581 -> 0.490; 0.641 -> 0.603; 0.720 -> 0.660 | Helped |
| Add the classifier to SSGAN (ablation) | SSGAN · Activity and PhysioNet | RMSE: 0.772 (1.68%); 0.770 (1.04%) | Helped |
| Add the discriminator to SSGAN (ablation) | SSGAN · Activity and PhysioNet | RMSE: 0.779 (2.57%); 0.771 (1.17%) | Helped |
| Add the temporal reminder matrix to SSGAN (ablation) | SSGAN · Activity and PhysioNet | RMSE: 0.773 (1.81%); 0.766 (0.52%) | Helped |
Closest papers by meaning
- Frequency-aware Generative Models for Multivariate Time Series Imputation (NeurIPS 2024 · similarity 0.90)
- Discretizing Continuous Time Series for Imputation with Masked Diffusion Training (NeurIPS 2026 · similarity 0.86)
- Motif-aware Graph Neural Networks for Networked Time Series Imputation (AAAI 2025 · similarity 0.86)
- Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification (NeurIPS 2025 · similarity 0.85)
- Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarios (AAAI 2025 · similarity 0.85)
- S4M: S4 for multivariate time series forecasting with Missing values (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.