So sánh phương pháp

	Pyraformer: Transformer Chú ý Kim Tự Tháp cho Dự báo Chuỗi Thời gian Tầm xa	Reformer: Bộ biến đổi hiệu quả cho chuỗi dài
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2022	2020
Người khởi xướng	Shizhan Liu et al.	Nikita Kitaev, Łukasz Kaiser & Anselm Levskaya
Loại	Pyramidal self-attention transformer for time-series forecasting	Memory-efficient attention-based sequence model
Công trình gốc	Liu, S., Yu, H., Liao, C., Li, J., Lin, W., Liu, A. X., & Dustdar, S. (2022). Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. ICLR.	Kitaev, N., Kaiser, Ł., & Levskaya, A. (2020). Reformer: The efficient transformer. ICLR.
Tên gọi khác	Pyramidal Attention Transformer, Pyraformer Transformer, Piramit Dikkat Dönüştürücüsü, Low-Complexity Transformer	Efficient Transformer, LSH Transformer, Locality-Sensitive Hashing Transformer, Verimli Dönüştürücü
Liên quan	3	2
Tóm tắt	Pyraformer is a Transformer-based model for long-range time-series forecasting introduced by Liu et al. at ICLR 2022. Its central innovation is a Pyramidal Attention Module (PAM) that organizes tokens into a multi-resolution hierarchy, enabling the model to capture temporal dependencies across multiple scales while keeping time and memory complexity at O(L log L) rather than the quadratic cost of vanilla self-attention.	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.