Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| FreTS: Viwanilishi vya Hisa za Mara kwa Mara kwa Utabiri wa Mfululizo wa Wakati× | FEDformer: Transformer Iliyoimarishwa kwa Masafa na Uozo× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2023 | 2022 |
| Mwanzilishi≠ | Kun Yi et al. | Tian Zhou et al. |
| Aina≠ | Frequency-domain MLP forecasting model | Frequency-domain decomposed Transformer for time-series forecasting |
| Chanzo asilia≠ | Yi, K., Zhang, Q., Fan, W., Wang, S., Wang, P., He, H., An, N., Lian, D., Cao, L., & Niu, Z. (2023). Frequency-domain MLPs are more effective learners in time series forecasting. NeurIPS. link ↗ | Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., & Jin, R. (2022). FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. ICML. link ↗ |
| Majina mbadala | Frequency-domain MLPs, FrequencyMLP, FreTS Forecaster, Frekans Alanı MLP | Frequency Enhanced Decomposed Transformer, FED-Transformer, Frequency Domain Transformer, Frekans Tabanlı Ayrıştırılmış Dönüştürücü |
| Zinazohusiana | 3 | 3 |
| Muhtasari≠ | FreTS is a time series forecasting architecture introduced by Yi et al. at NeurIPS 2023. It departs from Transformer-based designs by applying simple Multi-Layer Perceptrons (MLPs) entirely in the frequency domain. The model transforms input sequences with the Discrete Fourier Transform and then learns temporal and channel dependencies through complex-valued MLP layers, achieving competitive or superior long-term forecasting accuracy with substantially lower computational cost. | FEDformer is a Transformer-based architecture for long-term multivariate time-series forecasting, introduced by Zhou et al. at ICML 2022. Its core innovation is the combination of seasonal-trend decomposition with frequency-domain attention: instead of computing full token-to-token attention in the time domain, FEDformer projects queries, keys, and values into the frequency domain via Fourier or wavelet transforms and operates on a randomly selected subset of frequency components, achieving linear complexity while preserving global temporal structure. |
| ScholarGateSeti ya data ↗ |
|
|