Research map / Time series / Foundation models for time series
Hi-Time: Hierarchical Latent Prediction for Multivariate Time Series Classification
Kun Zeng, Binquan Wu, Qianli Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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-view representation fusion (MVRE) (ablation) | Hi-Time · AWR+IW average | accuracy: 0.781 -> 0.830 | Improved |
| add multi-scale fusion (ablation) | Hi-Time · AWR+IW average | accuracy: 0.807 -> 0.830 | Improved |
| add cross-variable fusion (ablation) | Hi-Time · AWR+IW average | accuracy: 0.820 -> 0.830 | Improved |
| add temporal dynamics fusion (ablation) | Hi-Time · AWR+IW average | accuracy: 0.816 -> 0.830 | Improved |
| add hierarchical latent prediction of semantic codes (ablation) | Hi-Time · AWR+IW average | accuracy: 0.806 -> 0.830 | Improved |
| use pre-trained GPT-2 weights instead of random init (ablation) | Hi-Time · AWR+IW average | accuracy: 0.784 -> 0.830 | Improved |
| add step-wise code prediction loss (MSL) (ablation) | Hi-Time · AWR+IW average | accuracy: 0.814 -> 0.830 | Improved |
| increase quantization depth L from 1 to 2 and beyond (ablation) | Hi-Time · AWR | accuracy | Mixed |
| increase codebook size K (ablation) | Hi-Time · AWR | accuracy | Hurt |
| increase codebook size K (ablation) | Hi-Time · IW | accuracy | Improved |
| hierarchical latent prediction on easier datasets (CT, FM, FD, MI) | Hi-Time · UEA datasets | accuracy: CT 0.982 vs TS-GAC 0.988 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- MPTSNet — MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification (AAAI 2025) · better on 3 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Time-LLM: Time Series Forecasting by Reprogramming Large Language Models (ICLR 2024 · similarity 0.90)
- TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment (AAAI 2025 · similarity 0.89)
- STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis (AAAI 2025 · similarity 0.89)
- $S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting (ICML 2024 · similarity 0.89)
- Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning (ICML 2024 · similarity 0.89)
- Large Pre-trained time series models for cross-domain Time series analysis tasks (NeurIPS 2024 · similarity 0.89)
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.
