Sammenlign metoder

	Autoformer: Transformer-dekomposition til langtids-tidsserieprognoser	Informer	TimesNet: Temporal 2D-Variation Modeling for Time Series
Fagområde	Dyb læring	Dyb læring	Dyb læring
Familie	Machine learning	Machine learning	Machine learning
Oprindelsesår	2021	2021	2023
Ophavsperson	Haixu Wu et al. (Tsinghua)	Zhou, H. et al.	Haixu Wu et al.
Type	Decomposition-based deep forecasting model	Transformer (ProbSparse self-attention)	2D convolutional time-series model
Oprindelig kilde	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.	Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2023). TimesNet: Temporal 2D-variation modeling for general time series analysis. ICLR.
Aliasser	Auto-Correlation Transformer, Decomposition Transformer, Series Decomposition Forecaster, Oto-Korelasyon Ayrışım Transformer	Informer — Uzun Dizi Transformer Tahmini, Informer transformer, ProbSparse attention forecaster	Temporal 2D-Variation Network, TimesNet Model, 2D Time-Series Network, Zamansal 2B Varyasyon Ağı
Relaterede	4	5	2
Resumé	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.	TimesNet is a general-purpose time-series model introduced by Wu et al. at ICLR 2023. Its central idea is that univariate or multivariate time series can be reinterpreted as collections of two-dimensional temporal maps by reshaping the 1D signal according to its dominant periodicities, detected via Fast Fourier Transform. This 1D-to-2D transformation exposes both intraperiod patterns (within one cycle) and interperiod trends (across cycles), enabling powerful 2D convolutional architectures to model temporal variation.