Usporedite metode

	Informer	Reformer: Učinkoviti Transformer za duge sekvence
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2021	2020
Tvorac	Zhou, H. et al.	Nikita Kitaev, Łukasz Kaiser & Anselm Levskaya
Vrsta	Transformer (ProbSparse self-attention)	Memory-efficient attention-based sequence model
Temeljni izvor	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.
Drugi nazivi	Informer — Uzun Dizi Transformer Tahmini, Informer transformer, ProbSparse attention forecaster	Efficient Transformer, LSH Transformer, Locality-Sensitive Hashing Transformer, Verimli Dönüştürücü
Srodne	5	2
Sažetak	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.