Research map / Time series / Long-term forecasting
SVP-T: A Shape-Level Variable-Position Transformer for Multivariate Time Series Classification
Rundong Zuo, Guozhong Li, Byron Choi, Sourav S Bhowmick, Daphne Ngar-yin Mah, Grace L.H. Wong
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 |
|---|---|---|---|
| use shape-level inputs instead of timestamp-level inputs | Transformer for MTSC · UEA archive | average rank: 7.483 -> 4.017 | Improved |
| replace the VP-layer with fully learnable positional encoding (ablation) | SVP-T · UEA archive | accuracy | Hurt |
| replace VP-based self-attention with original self-attention (ablation) | SVP-T · UEA archive | accuracy | Hurt |
| increase the number of input shapes L (ablation) | SVP-T · ArticularyWordRecognition, BasicMotions, EigenWorms, StandWalkJump | accuracy | Mixed |
Later papers that compared with this method
2 later accepted papers report SVP-T as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis (ICML 2026 · better on 1 of 1 shared result)
- MTP: Exploring Multimodal Urban Traffic Profiling with Modality Augmentation and Spectrum Fusion (AAAI 2026 · better on 0 of 1 shared result)
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
- Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification (NeurIPS 2024 · similarity 0.87)
- Time Series Representations with Hard-Coded Invariances (ICML 2025 · similarity 0.86)
- TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning (ICML 2024 · similarity 0.86)
- T-Rep: Representation Learning for Time Series using Time-Embeddings (ICLR 2024 · similarity 0.86)
- MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification (AAAI 2025 · similarity 0.85)
- TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning (ICML 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.
