Research map / Time series / Long-term forecasting
Hierarchical Deep Generative Models for Multi-Rate Multivariate 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 |
|---|---|---|---|
| add multi-rate latent structure (MR-DMM) to DMM (ablation) | DMM · MIMIC-III forecasting | MSE: 1.530 -> 1.061 | Helped |
| add hierarchical latent layers with auxiliary connections to DMM (HDMM) (ablation) | DMM · MIMIC-III forecasting | MSE: 1.530 -> 1.047 | Helped |
| add learnable switch mechanism for multi-rate hierarchy (MR-HDMM vs HDMM) (ablation) | HDMM · MIMIC-III forecasting | MSE: 1.047 -> 0.996 | Helped |
| add learnable switches to HDMM (ablation) | HDMM · USHCN forecasting | MSE: 0.626 -> 0.591 | Helped |
| add switches to HDMM on low-rate forecasting (ablation) | HDMM · MIMIC-III LSR forecasting | MSE: 1.076 -> 0.911 | Helped |
| replace single-rate VAR with MR-HDMM | VAR · USHCN forecasting | MSE: 2.415 -> 0.591 | Helped |
| replace VAR with MR-HDMM on MIMIC-III LSR | VAR · MIMIC-III LSR forecasting | MSE: 0.802 -> 0.911 | Mixed |
| use MR-HDMM instead of HDMM for interpolation (ablation) | HDMM · MIMIC-III in-sample interpolation | MSE: 3.790 -> 3.582 | Helped |
| use MR-HDMM instead of MR-DMM for interpolation (ablation) | MR-DMM · USHCN interpolation | MSE: 0.696 -> 0.626 | Helped |
| use MR-HDMM instead of MICE imputation | MICE · MIMIC-III out-sample interpolation | MSE: 7.580×102 -> 2.921 | Helped |
| use MR-HDMM instead of Simple-Mean | Simple-Mean · MIMIC-III in-sample interpolation | MSE: 3.812 -> 3.582 | Helped |
| add multi-rate and hierarchy to DMM for generative fit (ablation) | DMM · USHCN | log-likelihood lower bound: 2.37 -> 33.62 | Helped |
Closest papers by meaning
- HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.90)
- Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting (AAAI 2024 · similarity 0.88)
- TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data (AAAI 2025 · similarity 0.86)
- MSGNet: Learning Multi-Scale Inter-series Correlations for Multivariate Time Series Forecasting (AAAI 2024 · similarity 0.86)
- TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment (AAAI 2025 · similarity 0.86)
- CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables (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.