Research map / Time series / Causal and generative time series
BRITS: Bidirectional Recurrent Imputation for Time Series
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 |
|---|---|---|---|
| Replace STMVL with BRITS | Air Quality imputation · Air Quality | MAE: 12.12 -> 11.56 | Helped |
| Replace ImputeTS with BRITS | Health-care imputation · Health-care | MAE: 0.390 -> 0.281 | Helped |
| Replace M-RNN with BRITS | Human Activity imputation · Human Activity | MAE: 0.248 -> 0.219 | Helped |
| Add bidirectional dynamics and feature correlations (ablation) | RITS-I · Air Quality | MAE: 12.73 -> 11.56 | Helped |
| Add bidirectional dynamics and feature correlations (ablation) | RITS-I · Health-care | MAE: 0.395 -> 0.281 | Helped |
| Add bidirectional dynamics and feature correlations (ablation) | RITS-I · Human Activity | MAE: 0.240 -> 0.219 | Helped |
| Add feature correlations (ablation) | BRITS-I · Air Quality | MAE: 11.58 -> 11.56 | No clear effect |
| Add feature correlations (ablation) | BRITS-I · Health-care | MAE: 0.361 -> 0.281 | Helped |
| Add feature correlations (ablation) | BRITS-I · Human Activity | MAE: 0.220 -> 0.219 | No clear effect |
| Add bidirectional dynamics (ablation) | RITS · Air Quality | MAE: 12.19 -> 11.56 | Helped |
| Add bidirectional dynamics (ablation) | RITS · Health-care | MAE: 0.300 -> 0.281 | Helped |
| Add bidirectional dynamics (ablation) | RITS · Human Activity | MAE: 0.248 -> 0.219 | Helped |
Closest papers by meaning
- Frequency-aware Generative Models for Multivariate Time Series Imputation (NeurIPS 2024 · similarity 0.88)
- Motif-aware Graph Neural Networks for Networked Time Series Imputation (AAAI 2025 · similarity 0.88)
- Discretizing Continuous Time Series for Imputation with Masked Diffusion Training (NeurIPS 2026 · similarity 0.87)
- Task-oriented Time Series Imputation Evaluation via Generalized Representers (NeurIPS 2024 · similarity 0.87)
- Zero-shot Imputation with Foundation Inference Models for Dynamical Systems (ICLR 2025 · similarity 0.86)
- BayOTIDE: Bayesian Online Multivariate Time Series Imputation with Functional Decomposition (ICML 2024 · similarity 0.86)
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.