方法对比

	SegRNN：用于长期时间序列预测的段循环神经网络	门控循环单元 (GRU)	PatchTST
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	2014	2023
提出者	Shengsheng Lin et al.	Cho, K. et al.	Nie, Y. et al.
类型	Segment-based recurrent forecasting model	Gated recurrent neural network unit	Transformer for time series forecasting
开创性文献	Lin, S., Lin, W., Wu, W., Zhao, F., Mo, R., & Zhang, H. (2023). SegRNN: Segment recurrent neural network for long-term time series forecasting. arXiv preprint.	Cho, K. et al. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. EMNLP.	Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR.
别名	Segment RNN, Segment Recurrent Neural Network, SegRNN forecaster, Bölümlü Tekrarlayan Sinir Ağı	Kapılı Tekrarlayan Birim (GRU), gated recurrent unit, gated recurrent network	PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer
相关	3	5	3
摘要	SegRNN is a recurrent neural network architecture for long-term time series forecasting proposed by Shengsheng Lin et al. in 2023. Instead of processing one time step at a time, SegRNN partitions input sequences into fixed-length segments and feeds each segment as a single token into a GRU. This segment-based design drastically reduces the number of recurrent iterations, addressing the well-known difficulty RNNs face when modeling very long dependencies over many individual steps.	The Gated Recurrent Unit (GRU) is a gated recurrent neural network cell introduced by Cho and colleagues in 2014 that captures long-range dependencies in sequential data using update and reset gates, achieving performance comparable to LSTM with fewer parameters.	PatchTST is a patch-based Transformer architecture for time series forecasting, introduced by Nie and colleagues in 2023, that cuts each series into overlapping patches treated as tokens and processes channels independently. It balances computational efficiency with strong accuracy on long-horizon forecasting.