中文
相关论文

相关论文: Channel Dependence, Limited Lookback Windows, and …

200 篇论文

The balance between model capacity and generalization has been a key focus of recent discussions in long-term time series forecasting. Two representative channel strategies are closely associated with model expressivity and robustness,…

机器学习 · 计算机科学 2024-07-25 Tong Nie , Yuewen Mei , Guoyang Qin , Jian Sun , Wei Ma

Multivariate time-series analysis involves extracting informative representations from sequences of multiple interdependent variables, supporting tasks such as forecasting, imputation, and anomaly detection. In real-world scenarios, these…

机器学习 · 计算机科学 2026-05-19 Israel Zexer , Omri Azencot

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, there has been an…

机器学习 · 计算机科学 2023-04-12 Lu Han , Han-Jia Ye , De-Chuan Zhan

Time series forecasting methods generally fall into two main categories: Channel Independent (CI) and Channel Dependent (CD) strategies. While CI overlooks important covariate relationships, CD captures all dependencies without distinction,…

机器学习 · 计算机科学 2025-05-21 Yifan Hu , Guibin Zhang , Peiyuan Liu , Disen Lan , Naiqi Li , Dawei Cheng , Tao Dai , Shu-Tao Xia , Shirui Pan

Recently, channel-independent methods have achieved state-of-the-art performance in multivariate time series (MTS) forecasting. Despite reducing overfitting risks, these methods miss potential opportunities in utilizing channel dependence…

机器学习 · 计算机科学 2024-08-14 Lifan Zhao , Yanyan Shen

In multivariate time series forecasting (MTSF), accurately modeling the intricate dependencies among multiple variables remains a significant challenge due to the inherent limitations of traditional approaches. Most existing models adopt…

机器学习 · 计算机科学 2025-11-19 Yuchen Luo , Xinyu Li , Liuhua Peng , Mingming Gong

Time series forecasting has attracted significant attention in recent decades. Previous studies have demonstrated that the Channel-Independent (CI) strategy improves forecasting performance by treating different channels individually, while…

机器学习 · 计算机科学 2024-11-07 Jialin Chen , Jan Eric Lenssen , Aosong Feng , Weihua Hu , Matthias Fey , Leandros Tassiulas , Jure Leskovec , Rex Ying

Recent studies have attempted to refine the Transformer architecture to demonstrate its effectiveness in Long-Term Time Series Forecasting (LTSF) tasks. Despite surpassing many linear forecasting models with ever-improving performance, we…

机器学习 · 计算机科学 2024-12-30 Peiwang Tang , Weitai Zhang

There has been an emergence of various models for long-term time series forecasting. Recent studies have demonstrated that a single linear layer, using Channel Dependent (CD) or Channel Independent (CI) modeling, can even outperform a large…

机器学习 · 计算机科学 2023-12-20 Yuan Peiwen , Zhu Changsheng

Recently, significant advancements have been made in time-series forecasting research, with an increasing focus on analyzing the nature of time-series data, e.g, channel-independence (CI) and channel-dependence (CD), rather than solely…

机器学习 · 计算机科学 2023-08-04 Wei Li , Xiangxu Meng , Chuhao Chen , Jianing Chen

Time series forecasting has attracted significant attention in the field of AI. Previous works have revealed that the Channel-Independent (CI) strategy improves forecasting performance by modeling each channel individually, but it often…

机器学习 · 计算机科学 2026-03-17 Dongyuan Li , Shun Zheng , Chang Xu , Jiang Bian , Renhe Jiang

Long-term time series forecasting (LTSF) is widely recognized as a central challenge in data mining and machine learning. LTSF has increasingly evolved into a benchmark-driven ''GAME,'' where models are ranked, compared, and declared…

机器学习 · 计算机科学 2026-03-10 Thanapol Phungtua-eng , Yoshitaka Yamamoto

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as…

机器学习 · 计算机科学 2022-04-26 Jimeng Shi , Mahek Jain , Giri Narasimhan

Multivariate time series forecasting often struggles to capture long-range dependencies due to fixed lookback windows. Retrieval-augmented forecasting addresses this by retrieving historical segments from memory, but existing approaches…

机器学习 · 计算机科学 2026-04-08 Junhyeok Kang , Jun Seo , Soyeon Park , Sangjun Han , Seohui Bae , Hyeokjun Choe , Soonyoung Lee

Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational…

机器学习 · 计算机科学 2023-01-06 Yan Li , Xinjiang Lu , Haoyi Xiong , Jian Tang , Jiantao Su , Bo Jin , Dejing Dou

Time series forecasting (TSF) is a central problem in time series analysis. However, as the number of channels in time series datasets scales to the thousands or more, a scenario we define as High-Dimensional Time Series Forecasting…

机器学习 · 计算机科学 2025-09-30 Juntong Ni , Shiyu Wang , Zewen Liu , Xiaoming Shi , Xinyue Zhong , Zhou Ye , Wei Jin

Long-term time series forecasting (LTSF) remains challenging due to the trade-off between parallel efficiency and sequential modeling of temporal coherence. Direct multi-step forecasting (DMS) methods enable fast, parallel prediction of all…

机器学习 · 计算机科学 2026-02-03 Sunho Kim , Susik Yoon

Time Series Foundation Models (TSFMs) have borrowed the long context paradigm from natural language processing under the premise that feeding more history into the model improves forecast quality. But in stochastic domains, distant history…

机器学习 · 计算机科学 2026-05-12 Rishi Ahuja , Kumar Prateek , Simranjit Singh , Vijay Kumar

Recent studies have demonstrated the great power of Transformer models for time series forecasting. One of the key elements that lead to the transformer's success is the channel-independent (CI) strategy to improve the training robustness.…

机器学习 · 计算机科学 2024-02-19 Wang Xue , Tian Zhou , Qingsong Wen , Jinyang Gao , Bolin Ding , Rong Jin

Transformer-based models have emerged as powerful tools for multivariate time series forecasting (MTSF). However, existing Transformer models often fall short of capturing both intricate dependencies across variate and temporal dimensions…

机器学习 · 计算机科学 2024-06-10 Juncheng Liu , Chenghao Liu , Gerald Woo , Yiwei Wang , Bryan Hooi , Caiming Xiong , Doyen Sahoo
‹ 上一页 1 2 3 10 下一页 ›