中文
相关论文

相关论文: U-Mixer: An Unet-Mixer Architecture with Stationar…

200 篇论文

Although the Transformer has been the dominant architecture for time series forecasting tasks in recent years, a fundamental challenge remains: the permutation-invariant self-attention mechanism within Transformers leads to a loss of…

机器学习 · 计算机科学 2024-10-15 Zeying Gong , Yujin Tang , Junwei Liang

Multivariate time series data provide a robust framework for future predictions by leveraging information across multiple dimensions, ensuring broad applicability in practical scenarios. However, their high dimensionality and mixing…

机器学习 · 计算机科学 2024-11-28 Xuanbing Zhu , Dunbin Shen , Zhongwen Rao , Huiyi Ma , Yingguang Hao , Hongyu Wang

As environments evolve, temporal distribution shifts can degrade time series forecasting performance. A straightforward solution is to adapt to nonstationary changes while preserving stationary dependencies. Hence, some methods disentangle…

机器学习 · 计算机科学 2025-03-11 Zijian Li , Ruichu Cai , Zhenhui Yang , Haiqin Huang , Guangyi Chen , Yifan Shen , Zhengming Chen , Xiangchen Song , Kun Zhang

Time series forecasting is important in many fields that require accurate predictions for decision-making. Patching techniques, commonly used and effective in time series modeling, help capture temporal dependencies by dividing the data…

机器学习 · 计算机科学 2026-02-03 Xiangfei Qiu , Xvyuan Liu , Tianen Shen , Xingjian Wu , Hanyin Cheng , Bin Yang , Jilin Hu

Multivariate time series forecasting remains a challenge due to the complexity of local temporal dynamics and global dependencies across multiple variables. In this paper, we propose \textbf{N}eighboring \textbf{P}atching \textbf{Mixer}…

机器学习 · 计算机科学 2026-05-11 Jung Min Choi , Vijaya Krishna Yalavarthi , Lars Schmidt-Thieme

Time series forecasting (TSF) is crucial in fields like economic forecasting, weather prediction, traffic flow analysis, and public health surveillance. Real-world time series data often include noise, outliers, and missing values, making…

机器学习 · 计算机科学 2024-07-09 Quangao Liu , Ruiqi Li , Maowei Jiang , Wei Yang , Chen Liang , LongLong Pang , Zhuozhang Zou

Forecasting long-term time series in IoT environments remains a significant challenge due to the non-stationary and multi-scale characteristics of sensor signals. Furthermore, error accumulation causes a decrease in forecast quality when…

机器学习 · 计算机科学 2025-11-10 Qianyang Li , Xingjun Zhang , Peng Tao , Shaoxun Wang , Yancheng Pan , Jia Wei

Multivariate time series forecasting has been widely used in various practical scenarios. Recently, Transformer-based models have shown significant potential in forecasting tasks due to the capture of long-range dependencies. However,…

机器学习 · 计算机科学 2023-02-10 Zhe Li , Zhongwen Rao , Lujia Pan , Zenglin Xu

Time series data is prevalent across numerous fields, necessitating the development of robust and accurate forecasting models. Capturing patterns both within and between temporal and multivariate components is crucial for reliable…

机器学习 · 计算机科学 2025-11-21 Maurice Kraus , Felix Divo , Devendra Singh Dhami , Kristian Kersting

Spatial-temporal forecasting systems play a crucial role in addressing numerous real-world challenges. In this paper, we investigate the potential of addressing spatial-temporal forecasting problems using general time series forecasting…

Time series forecasting task predicts future trends based on historical information. Transformer-based U-Net architectures, despite their success in medical image segmentation, have limitations in both expressiveness and computation…

机器学习 · 计算机科学 2024-09-10 Jiang You , Arben Cela , René Natowicz , Jacob Ouanounou , Patrick Siarry

Multivariate time series forecasting is widely applied in fields such as transportation, energy, and finance. However, the data commonly suffers from issues of multi-scale characteristics, weak correlations, and noise interference, which…

机器学习 · 计算机科学 2026-03-02 Xiang Ao

Time series forecasting is crucial for various applications, such as weather forecasting, power load forecasting, and financial analysis. In recent studies, MLP-mixer models for time series forecasting have been shown as a promising…

机器学习 · 计算机科学 2024-12-24 Md Mahmuddun Nabi Murad , Mehmet Aktukmak , Yasin Yilmaz

Real-world time-series datasets are often multivariate with complex dynamics. To capture this complexity, high capacity architectures like recurrent- or attention-based sequential deep learning models have become popular. However, recent…

机器学习 · 计算机科学 2023-09-12 Si-An Chen , Chun-Liang Li , Nate Yoder , Sercan O. Arik , Tomas Pfister

Forecasting irregularly sampled multivariate time series with missing values (IMTS) is a fundamental challenge in domains such as healthcare, climate science, and biology. While recent advances in vision and time series forecasting have…

机器学习 · 计算机科学 2026-02-27 Christian Klötergens , Tim Dernedde , Lars Schmidt-Thieme , Vijaya Krishna Yalavarthi

Irregular multivariate time series forecasting (IMTSF) is challenging due to non-uniform sampling and variable asynchronicity. These irregularities violate the equidistant assumptions of standard models, hindering local temporal modeling…

机器学习 · 计算机科学 2026-02-03 Xiangfei Qiu , Kangjia Yan , Xvyuan Liu , Xingjian Wu , Jilin Hu

Recently, Transformer-base models have made significant progress in the field of time series prediction which have achieved good results and become baseline models beyond Dlinear. The paper proposes an U-Net time series prediction model…

机器学习 · 计算机科学 2024-06-07 Li Chu , Xiao Bingjia , Yuan Qiping

Multivariate time series forecasting involves predicting future values based on historical observations. However, existing approaches primarily rely on predefined single-scale patches or lack effective mechanisms for multi-scale feature…

机器学习 · 计算机科学 2025-09-24 Huanyao Zhang , Jiaye Lin , Wentao Zhang , Haitao Yuan , Guoliang Li

As multimodal data proliferates across diverse real-world applications, leveraging heterogeneous information such as texts and timestamps for accurate time series forecasting (TSF) has become a critical challenge. While diffusion models…

机器学习 · 计算机科学 2025-12-09 Da Zhang , Bingyu Li , Zhuyuan Zhao , Junyu Gao , Feiping Nie , Xuelong Li

In long-term multivariate time series forecasting, effectively capturing both periodic patterns and residual dynamics is essential. To address this within standard deep learning benchmark settings, we propose the Hierarchical Patching Mixer…

机器学习 · 计算机科学 2026-02-20 Jung Min Choi , Vijaya Krishna Yalavarthi , Lars Schmidt-Thieme
‹ 上一页 1 2 3 10 下一页 ›