Módszerek összehasonlítása
Tekintse át a kiválasztott módszereket egymás mellett; az eltérő sorok kiemelve jelennek meg.
| Crossformer× | iTransformer: Invertált transzformer többváltozós idősor-előrejelzéshez× | |
|---|---|---|
| Tudományterület | Mélytanulás | Mélytanulás |
| Módszercsalád | Machine learning | Machine learning |
| Keletkezés éve≠ | 2023 | 2024 |
| Megalkotó≠ | Yunhao Zhang & Junchi Yan | Yong Liu et al. |
| Típus≠ | Transformer-based multivariate time-series forecasting model | Inverted-attention sequence model |
| Alapmű≠ | Zhang, Y., & Yan, J. (2023). Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. ICLR. link ↗ | Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., & Long, M. (2024). iTransformer: Inverted transformers are effective for time series forecasting. ICLR. link ↗ |
| Alternatív nevek≠ | Cross-Dimension Dependency Transformer, Crossformer TSF, Çapraz-Boyut Bağımlılık Transformatörü | Inverted Transformer, iTransformer for Time Series, Inverted Attention Transformer, Ters Transformer |
| Kapcsolódó≠ | 3 | 2 |
| Összefoglaló≠ | Crossformer is a Transformer-based architecture for multivariate time series forecasting, introduced by Yunhao Zhang and Junchi Yan at ICLR 2023. Unlike earlier Transformer variants that treat each variate independently, Crossformer explicitly models cross-dimension dependencies alongside temporal patterns. It achieves this through a two-stage attention design — cross-time and cross-dimension — applied over segment-level embeddings organized in a hierarchical encoder, enabling the model to capture both intra-variate dynamics and inter-variate correlations simultaneously. | iTransformer is a deep-learning architecture for multivariate time-series forecasting introduced by Liu et al. at ICLR 2024. Its defining idea is to invert the conventional Transformer tokenisation strategy: instead of treating each time step as a token, iTransformer treats each variate (sensor channel or feature series) as a single token whose embedding encodes the full observed look-back window. Self-attention is then applied across variates to capture inter-series dependencies, while a feed-forward network within each token learns temporal patterns. |
| ScholarGateAdatkészlet ↗ |
|
|