Research map / Time series / Long-term forecasting
Numerion: A Multi-Hypercomplex Model for Time Series Forecasting
Hanzhong Cao, WenBo Yan, Ying Tan
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-Level Patch Embedding (ablation) | Numerion · Electricity (P=96) | MSE: 0.164 -> 0.152 | Improved |
| add Multi-Level Patch Embedding (ablation) | Numerion · ETTh1 (P=720) | MSE: 0.455 -> 0.449 | Improved |
| add Adaptive Fusion (ablation) | Numerion · Electricity (P=96) | MSE: 0.177 -> 0.152 | Improved |
| add Adaptive Fusion (ablation) | Numerion · ETTh1 (P=720) | MSE: 0.450 -> 0.449 | Improved |
| add Sede (16-dim) RHR-MLP (ablation) | Numerion · Electricity (P=96) | MSE: 0.166 -> 0.152 | Improved |
| add Octonion RHR-MLP (ablation) | Numerion · Electricity (P=96) | MSE: 0.161 -> 0.152 | Improved |
| add Quaternion RHR-MLP (ablation) | Numerion · Electricity (P=96) | MSE: 0.160 -> 0.152 | Improved |
| add Real RHR-MLP (ablation) | Numerion · Electricity (P=96) | MSE: 0.160 -> 0.152 | Improved |
| add Complex RHR-MLP (ablation) | Numerion · Electricity (P=96) | MSE: 0.156 -> 0.152 | Improved |
| use multiple hypercomplex spaces instead of only the real space (ablation) | Numerion RHR-MLP · Electricity (P=96) | MSE: 0.235 -> 0.152 | Improved |
| use Sede space only instead of all five spaces (ablation) | Numerion RHR-MLP · Electricity (P=96) | MSE: 0.180 -> 0.152 | Improved |
| add full HNTanh activation to hypercomplex layer (ablation) | hypercomplex MLP · ETTh1 (P=96) | MSE: 0.370 -> 0.359 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.
- TimeMixer — TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting (ICLR 2024) · better on 0 of 1 shared result
- iTransformer — iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (ICLR 2024) · 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
- HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting (ICML 2025 · similarity 0.88)
- TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting (NeurIPS 2025 · similarity 0.87)
- HyperMixer: Specializable Hypergraph Channel Mixing for Long-term Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.87)
- HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.87)
- TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting (NeurIPS 2025 · similarity 0.87)
- Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer (ICML 2025 · 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.
