Порівняння методів

	Нестаціонарний Трансформер	Autoformer	Informer
Галузь	Глибоке навчання	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning	Machine learning
Рік появи	2022	2021	2021
Автор методу	Yong Liu et al.	Haixu Wu et al. (Tsinghua)	Zhou, H. et al.
Тип	Transformer-based time-series forecasting model	Decomposition-based deep forecasting model	Transformer (ProbSparse self-attention)
Основоположне джерело	Liu, Y., Wu, H., Wang, J., & Long, M. (2022). Non-stationary transformers: Exploring the stationarity in time series forecasting. NeurIPS.	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.
Інші назви	NS-Transformer, Non-stationary Transformer Network, Stationarization-based Transformer, Durağan-Olmayan Transformer	Auto-Correlation Transformer, Decomposition Transformer, Series Decomposition Forecaster, Oto-Korelasyon Ayrışım Transformer	Informer — Uzun Dizi Transformer Tahmini, Informer transformer, ProbSparse attention forecaster
Пов'язані	3	4	5
Підсумок	Non-stationary Transformer is a Transformer-based time-series forecasting architecture introduced by Yong Liu, Haixu Wu, Jianmin Wang, and Mingsheng Long at NeurIPS 2022. It addresses a fundamental tension in applying Transformers to real-world time series: over-stationarization during preprocessing strips out non-stationary signals that carry predictive information, while raw non-stationary inputs cause attention to collapse. The model resolves this through series stationarization paired with a novel de-stationary attention mechanism that restores the original temporal distribution in predictions.	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.