So sánh phương pháp

	Autoformer: Biến đổi phân tách cho dự báo chuỗi thời gian dài hạn	FEDformer: Transformer phân rã tăng cường tần số
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2021	2022
Người khởi xướng	Haixu Wu et al. (Tsinghua)	Tian Zhou et al.
Loại	Decomposition-based deep forecasting model	Frequency-domain decomposed Transformer for time-series forecasting
Công trình gốc	Wu, H., Xu, J., Wang, J., & Long, M. (2021). Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NeurIPS, 34.	Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., & Jin, R. (2022). FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. ICML.
Tên gọi khác	Auto-Correlation Transformer, Decomposition Transformer, Series Decomposition Forecaster, Oto-Korelasyon Ayrışım Transformer	Frequency Enhanced Decomposed Transformer, FED-Transformer, Frequency Domain Transformer, Frekans Tabanlı Ayrıştırılmış Dönüştürücü
Liên quan	4	3
Tóm tắt	Autoformer is a deep learning architecture for long-term time-series forecasting, introduced by Wu et al. from Tsinghua University at NeurIPS 2021. It replaces the standard self-attention mechanism with an Auto-Correlation mechanism that exploits periodic dependencies in the frequency domain, and embeds a progressive series decomposition block throughout the encoder and decoder to separately model trend and seasonal components.	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.