Compara mètodes

	FEDformer: Transformer millorat per freqüència per a la descomposició	FiLM: Frequency Improved Legendre Memory Model
Camp	Aprenentatge profund	Aprenentatge profund
Família	Machine learning	Machine learning
Any d'origen	2022	2022
Autor original	Tian Zhou et al.	Tian Zhou et al.
Tipus	Frequency-domain decomposed Transformer for time-series forecasting	Frequency-domain time-series forecasting model
Font seminal	Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., & Jin, R. (2022). FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. ICML.	Zhou, T., Ma, Z., Wen, Q., Sun, L., Yao, T., Yin, W., & Jin, R. (2022). FiLM: Frequency improved Legendre memory model for long-term time series forecasting. NeurIPS.
Àlies	Frequency Enhanced Decomposed Transformer, FED-Transformer, Frequency Domain Transformer, Frekans Tabanlı Ayrıştırılmış Dönüştürücü	Frequency Improved Legendre Memory, FiLM Forecaster, Legendre Frequency Model, Frekans Tabanlı Legendre Bellek Modeli
Relacionats	3	3
Resum	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.	FiLM is a long-term time-series forecasting architecture introduced by Tian Zhou and colleagues at NeurIPS 2022. It combines Legendre polynomial projections of the historical input with learnable frequency-domain filters applied to the resulting coefficient sequences. By representing history as a compact set of polynomial coefficients and filtering those coefficients in the frequency domain, FiLM enables efficient extrapolation over long prediction horizons without the quadratic cost of full self-attention.