paper-with-me

홈 › Papers

Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting

2022-05-28 · Yong liu, Haixu Wu, Jianmin Wang, Mingsheng Long

Transformers have shown great power in time series forecasting due to their global-range modeling ability. However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time. Previous studies primarily adopt stationarization to attenuate the non-stationarity of original series for better predictability. But the stationarized series deprived of inherent non-stationarity can be less instructive for real-world bursty events forecasting. This problem, termed over-stationarization in this paper, leads Transformers to generate indistinguishable temporal attentions for different series and impedes the predictive capability of deep models. To tackle the dilemma between series predictability and model capability, we propose Non-stationary Transformers as a generic framework with two interdependent modules: Series Stationarization and De-stationary Attention. Concretely, Series Stationarization unifies the statistics of each input and converts the output with restored statistics for better predictability. To address the over-stationarization problem, De-stationary Attention is devised to recover the intrinsic non-stationary information into temporal dependencies by approximating distinguishable attentions learned from raw series. Our Non-stationary Transformers framework consistently boosts mainstream Transformers by a large margin, which reduces MSE by 49.43% on Transformer, 47.34% on Informer, and 46.89% on Reformer, making them the state-of-the-art in time series forecasting. Code is available at this repository: https://github.com/thuml/Nonstationary_Transformers.

📄 PDF Abstract BibTeX arXiv:2205.14415

Code (2)

WenjieDu/PyPOTS 공식 구현 pytorch
thuml/Nonstationary_Transformers pytorch

Tasks

Time SeriesTime Series AnalysisTime Series Forecasting

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Reversible Residual Block 설명 없음

Similar Papers 제목 키워드 기반

Exploring Over-stationarization in Deep Learning-based Bus/Tram Arrival Time Prediction: Analysis and Non-stationary Effect Recovery

2025-08-31 · Zirui Li, Bin Yang, Meng Wang arxiv

Arrival time prediction (ATP) of public transport vehicles is essential in improving passenger experience and supporting traffic management. Deep learning has demonstrated outstanding performance in ATP due to its abilit…

Lightweight Channel-wise Dynamic Fusion Model: Non-stationary Time Series Forecasting via Entropy Analysis

2025-03-04 · Tianyu Jia, Zongxia Xie, Yanru Sun, Dilfira Kudrat 외

Non-stationarity is an intrinsic property of real-world time series and plays a crucial role in time series forecasting. Previous studies primarily adopt instance normalization to attenuate the non-stationarity of origin…

Time SeriesTime Series Forecasting

W-Transformers : A Wavelet-based Transformer Framework for Univariate Time Series Forecasting

2022-09-08 · Lena Sasal, Tanujit Chakraborty, Abdenour Hadid

Deep learning utilizing transformers has recently achieved a lot of success in many vital areas such as natural language processing, computer vision, anomaly detection, and recommendation systems, among many others. Amon…

Anomaly DetectionRecommendation SystemsRepresentation LearningTime Series+3

Towards Non-Stationary Time Series Forecasting with Temporal Stabilization and Frequency Differencing

2025-11-11 · Junkai Lu, Peng Chen, Chenjuan Guo, Yang Shu 외 arxiv

Time series forecasting is critical for decision-making across dynamic domains such as energy, finance, transportation, and cloud computing. However, real-world time series often exhibit non-stationarity, including tempo…

Time Series Forecasting

Stationarity Exploration for Multivariate Time Series Forecasting

2025-08-12 · Hao Liu, Chun Yang, Zhang xiaoxing, Rui Ma 외 arxiv

Deep learning-based time series forecasting has found widespread applications. Recently, converting time series data into the frequency domain for forecasting has become popular for accurately exploring periodic patterns…

Multivariate Time Series Forecasting