Multivariate Time Series Forecasting

Multivariate time series forecasting aims to predict the future values of multiple interconnected time series, a crucial task across diverse fields like finance and healthcare. Current research emphasizes improving model accuracy and robustness, focusing on architectures like Transformers and Graph Neural Networks, as well as addressing challenges such as non-stationarity, missing data, and computational efficiency through techniques like frequency domain analysis and lightweight model designs. These advancements are significant for improving decision-making in various applications by providing more accurate and reliable predictions, particularly in scenarios with high-dimensional data and complex temporal dependencies.

Papers

February 25, 2024

PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations
Shiyi Qi, Zenglin Xu, Yiduo Li, Liangjian Wen, Qingsong Wen, Qifan Wang, Yuan Qi
Partial Differential Equation Visual Perspective Multivariate Time Series Multivariate Time Series Forecasting SpatioTemporal Data Time Index

February 23, 2024

Deep Coupling Network For Multivariate Time Series Forecasting
Kun Yi, Qi Zhang, Hui He, Kaize Shi, Liang Hu, Ning An, Zhendong Niu
Multivariate Time Series Multivariate Time Series Forecasting Inter Series

February 20, 2024

February 12, 2024

Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
Cheng Feng, Long Huang, Denis Krompass
Zero Shot Foundation Model Multivariate Time Series Forecasting Channel Prediction Time Transformer Shape Prediction Parametric Curve

February 8, 2024

Attention as Robust Representation for Time Series Forecasting
PeiSong Niu, Tian Zhou, Xue Wang, Liang Sun, Rong Jin
Human Attention Transformer Based Model Time Series Forecasting Attention Map Multivariate Time Series Forecasting Robust Representation Attention Weight

January 31, 2024

Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
Lifan Zhao, Yanyan Shen
Time Series Forecasting Multivariate Time Series Multivariate Time Series Forecasting Forecasting Performance Channel Wise Aggregate Level Indicator Deterministic Forecast Lead Lag

January 3, 2024

Kernel-U-Net: Multivariate Time Series Forecasting using Custom Kernels
Jiang You, Arben Cela, René Natowicz, Jacob Ouanounou, Patrick Siarry
Time Series Forecasting U Net Multivariate Time Series Forecasting Input Time Series

December 31, 2023

MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting
Wanlin Cai, Yuxuan Liang, Xianggen Liu, Jianshuai Feng, Yuankai Wu
Multi Scale Multivariate Time Series Forecasting

December 22, 2023

Spatiotemporal-Linear: Towards Universal Multivariate Time Series Forecasting
Aiyinsi Zuo, Haixi Zhang, Zirui Li, Ce Zheng
Multivariate Time Series Forecasting Time Series Prediction Spatio tempOral Step Prediction

December 11, 2023

December 4, 2023

Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach
Jinguo Cheng, Ke Li, Yuxuan Liang, Lijun Sun, Junchi Yan, Yuankai Wu
Multivariate Time Series Forecasting Urban Mobility

November 21, 2023

Hierarchical Joint Graph Learning and Multivariate Time Series Forecasting
Juhyeon Kim, Hyungeun Lee, Seungwon Yu, Ung Hwang, Wooyul Jung, Miseon Park, Kijung Yoon
Multivariate Time Series Temporal Dependency Multivariate Time Series Forecasting Multivariate Signal

November 19, 2023

TimeSQL: Improving Multivariate Time Series Forecasting with Multi-Scale Patching and Smooth Quadratic Loss
Site Mo, Haoxin Wang, Bixiong Li, Songhai Fan, Yuankai Wu, Xianggen Liu
Multivariate Time Series Forecasting Time Series Prediction Smooth Loss Function World Dynamic Long Range Correlation Multi Scale Patch Temporal Query

November 10, 2023

FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
Kun Yi, Qi Zhang, Wei Fan, Hui He, Liang Hu, Pengyang Wang, Ning An, Longbing Cao, Zhendong Niu
Multivariate Time Series Multivariate Time Series Forecasting Graph Perspective Fourier Net Space Time Multidimensional Graph Fourier Transformation

October 31, 2023

October 22, 2023

Pyramidal Hidden Markov Model For Multivariate Time Series Forecasting
YeXin Huang
Multivariate Time Series Forecasting Hidden Markov Model Pyramid Network

October 15, 2023

UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting
Xu Liu, Junfeng Hu, Yuan Li, Shizhe Diao, Yuxuan Liang, Bryan Hooi, Roger Zimmermann
Time Series Multivariate Time Series Forecasting Unified Model

Multivariate Time Series Forecasting

Papers

PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations

Deep Coupling Network For Multivariate Time Series Forecasting

Structural Knowledge Informed Continual Multivariate Time Series Forecasting

Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling

Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction

Attention as Robust Representation for Time Series Forecasting

Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators

Kernel-U-Net: Multivariate Time Series Forecasting using Custom Kernels

MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting

Spatiotemporal-Linear: Towards Universal Multivariate Time Series Forecasting

Dozerformer: Sequence Adaptive Sparse Transformer for Multivariate Time Series Forecasting

Dance of Channel and Sequence: An Efficient Attention-Based Approach for Multivariate Time Series Forecasting

Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach

Hierarchical Joint Graph Learning and Multivariate Time Series Forecasting

TimeSQL: Improving Multivariate Time Series Forecasting with Multi-Scale Patching and Smooth Quadratic Loss

FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective

BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis

AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Data

Pyramidal Hidden Markov Model For Multivariate Time Series Forecasting

UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting