方法对比

	Koopa：用于非平稳时间序列的 Koopman 预测器	DLinear：时间序列预测的分解线性模型	非平稳Transformer
领域	深度学习	深度学习	深度学习
方法族	Machine learning	Machine learning	Machine learning
起源年份	2023	2023	2022
提出者	Yong Liu et al.	Ailing Zeng et al.	Yong Liu et al.
类型	Koopman operator-based time-series forecasting model	Decomposition-based linear forecasting model	Transformer-based time-series forecasting model
开创性文献	Liu, Y., Li, C., Wang, J., & Long, M. (2023). Koopa: Learning non-stationary time series dynamics with Koopman predictors. NeurIPS.	Zeng, A., Chen, M., Zhang, L., & Xu, Q. (2023). Are transformers effective for time series forecasting? AAAI.	Liu, Y., Wu, H., Wang, J., & Long, M. (2022). Non-stationary transformers: Exploring the stationarity in time series forecasting. NeurIPS.
别名	Koopman Predictor, Koopman-based Time-Series Model, Koopa Forecaster, Koopman Tahmincisi	Decomposition Linear, DLinear Forecaster, Linear Decomposition Model, Ayrışım Doğrusal Modeli	NS-Transformer, Non-stationary Transformer Network, Stationarization-based Transformer, Durağan-Olmayan Transformer
相关	3	3	3
摘要	Koopa is a deep learning model for time-series forecasting introduced by Yong Liu, Chang Li, Jianmin Wang, and Mingsheng Long at NeurIPS 2023. It addresses the challenge of non-stationarity by disentangling time series into stationary and non-stationary components, then modeling the non-stationary dynamics using a learned approximation of the Koopman operator — a mathematical framework that lifts nonlinear systems into a linear space for tractable long-horizon prediction.	DLinear is a lightweight time series forecasting model introduced by Zeng et al. at AAAI 2023. It challenges the prevailing assumption that Transformer-based architectures are necessary for accurate long-horizon forecasting. The model decomposes an input sequence into trend and seasonal components using a moving average filter, then applies separate single-layer linear transformations to each component before summing their outputs to produce the final forecast.	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.