paper-with-me

홈 › Papers

Revisiting Attention for Multivariate Time Series Forecasting

2024-07-18 · Haixiang Wu

Current Transformer methods for Multivariate Time-Series Forecasting (MTSF) are all based on the conventional attention mechanism. They involve sequence embedding and performing a linear projection of Q, K, and V, and then computing attention within this latent space. We have never delved into the attention mechanism to explore whether such a mapping space is optimal for MTSF. To investigate this issue, this study first proposes Frequency Spectrum attention (FSatten), a novel attention mechanism based on the frequency domain space. It employs the Fourier transform for embedding and introduces Multi-head Spectrum Scaling (MSS) to replace the conventional linear mapping of Q and K. FSatten can accurately capture the periodic dependencies between sequences and outperform the conventional attention without changing mainstream architectures. We further design a more general method dubbed Scaled Orthogonal attention (SOatten). We propose an orthogonal embedding and a Head-Coupling Convolution (HCC) based on the neighboring similarity bias to guide the model in learning comprehensive dependency patterns. Experiments show that FSatten and SOatten surpass the SOTA which uses conventional attention, making it a good alternative as a basic attention mechanism for MTSF. The codes and log files will be released at: https://github.com/Joeland4/FSatten-SOatten.

📄 PDF Abstract BibTeX arXiv:2407.13806

Code (1)

joeland4/fsatten-soatten 공식 구현

Tasks

Multivariate Time Series ForecastingTime SeriesTime Series Forecasting

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Residual Connection 설명 없음
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

TwinS: Revisiting Non-Stationarity in Multivariate Time Series Forecasting

2024-06-06 · Jiaxi Hu, Qingsong Wen, Sijie Ruan, Li Liu 외

Recently, multivariate time series forecasting tasks have garnered increasing attention due to their significant practical applications, leading to the emergence of various deep forecasting models. However, real-world ti…

Multivariate Time Series ForecastingTime SeriesTime Series Forecasting

The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting

2023-04-11 · Lu Han, Han-Jia Ye, De-Chuan Zhan

Multivariate time series data comprises various channels of variables. The multivariate forecasting models need to capture the relationship between the channels to accurately predict future values. However, recently, the…

Multivariate Time Series ForecastingTime SeriesTime Series Forecasting

Revisiting Multivariate Time Series Forecasting with Missing Values

2025-09-27 · Jie Yang, Yifan Hu, Kexin Zhang, Luyang Niu 외 arxiv

Missing values are common in real-world time series, and multivariate time series forecasting with missing values (MTSF-M) has become a crucial area of research for ensuring reliable predictions. To address the challenge…

Multivariate Time Series Forecasting

Expressing Multivariate Time Series as Graphs with Time Series Attention Transformer

2022-08-19 · William T. Ng, K. Siu, Albert C. Cheung, Michael K. Ng

A reliable and efficient representation of multivariate time series is crucial in various downstream machine learning tasks. In multivariate time series forecasting, each variable depends on its historical values and the…

Multivariate Time Series ForecastingRepresentation LearningTime SeriesTime Series Analysis+1

DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting

2019-11-03 · CIKM ’19, November 3–7, 2019, Beijing, China 2019 11 · Siteng Huang Donglin Wang∗

Multivariate time series forecasting has attracted wide attention in areas, such as system, traffic, and finance. The difficulty of the task lies in that traditional methods fail to capture complicated nonlinear dependen…

Multivariate Time Series ForecastingTime SeriesTime Series AnalysisTime Series Forecasting