השוואת שיטות

	Autoformer: טרנספורמר מבוסס פירוק לחיזוי סדרות עתיות ארוכות טווח	מְיַדֵּעַ	הרפורמר: הטרנספורמר היעיל לרצפים ארוכים
תחום	למידה עמוקה	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning	Machine learning
שנת המקור	2021	2021	2020
הוגה השיטה	Haixu Wu et al. (Tsinghua)	Zhou, H. et al.	Nikita Kitaev, Łukasz Kaiser & Anselm Levskaya
סוג	Decomposition-based deep forecasting model	Transformer (ProbSparse self-attention)	Memory-efficient attention-based sequence model
מקור מכונן	Wu, H., Xu, J., Wang, J., & Long, M. (2021). Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NeurIPS, 34.	Zhou, H. et al. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. AAAI.	Kitaev, N., Kaiser, Ł., & Levskaya, A. (2020). Reformer: The efficient transformer. ICLR.
כינויים	Auto-Correlation Transformer, Decomposition Transformer, Series Decomposition Forecaster, Oto-Korelasyon Ayrışım Transformer	Informer — Uzun Dizi Transformer Tahmini, Informer transformer, ProbSparse attention forecaster	Efficient Transformer, LSH Transformer, Locality-Sensitive Hashing Transformer, Verimli Dönüştürücü
קשורות	4	5	2
תקציר	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.	Informer is a Transformer-based model introduced by Zhou et al. in 2021 for long-sequence time-series forecasting, using a ProbSparse self-attention mechanism that lowers the computational complexity of the standard Transformer to O(L log L). It is built for problems that demand predictions across thousands of future steps.	The Reformer is an efficient variant of the Transformer architecture introduced by Kitaev, Kaiser, and Levskaya at ICLR 2020. It addresses the prohibitive O(L²) memory and computational cost of standard self-attention for long sequences. The key innovations are locality-sensitive hashing (LSH) attention, which approximates full attention in O(L log L) time, and reversible residual layers that dramatically reduce activation memory during training.