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

June 11, 2024

DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting
Yuxuan Shu, Vasileios Lampos
Time Series Forecasting Multivariate Time Series Autoregressive Model Multivariate Time Series Forecasting Deformable Attention

June 8, 2024

CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecasting
Chaolv Zeng, Zhanyu Liu, Guanjie Zheng, Linghe Kong
State Space Model Multivariate Time Series Mamba in Mamba Multivariate Time Series Forecasting Complex Time Series Linear Forecasting

June 7, 2024

UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting
Juncheng Liu, Chenghao Liu, Gerald Woo, Yiwei Wang, Bryan Hooi, Caiming Xiong, Doyen Sahoo
Transformer Model Transformer Based Model Multivariate Time Series Forecasting Question Based Dependency Inter Series

June 6, 2024

TwinS: Revisiting Non-Stationarity in Multivariate Time Series Forecasting
Jiaxi Hu, Qingsong Wen, Sijie Ruan, Li Liu, Yuxuan Liang
Temporal Attention Multivariate Time Series Forecasting Non Stationarity Identical Twin Temporal Neural Network Deep Time Series Forecasting

June 3, 2024

TimeCMA: Towards LLM-Empowered Time Series Forecasting via Cross-Modality Alignment
Chenxi Liu, Qianxiong Xu, Hao Miao, Sun Yang, Lingzheng Zhang, Cheng Long, Ziyue Li, Rui Zhao
Time Series Forecasting LLM Based Multivariate Time Series Forecasting Temporal Embeddings Cross Modality Alignment

May 28, 2024

ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks
Wanlin Cai, Kun Wang, Hao Wu, Xiaoxu Chen, Yuankai Wu
Graph Neural Network Time Series Forecasting Multivariate Time Series Forecasting GNN Based Forecast Utterance Group Convolutional Neural Network

May 23, 2024

MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs
Georgios Chatzigeorgakidis, Konstantinos Lentzos, Dimitrios Skoutas
Large Language Model Multivariate Time Series Multivariate Time Series Forecasting Keystroke Prediction Zero Shot LLM

May 22, 2024

Interpretable Multivariate Time Series Forecasting Using Neural Fourier Transform
Noam Koren, Kira Radinsky
Time Series Multivariate Time Series Forecasting Prediction Horizon Fourier Neural

May 19, 2024

VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting
Yingnan Yang, Qingling Zhu, Jianyong Chen
Multivariate Time Series Multivariate Time Series Forecasting Cross Correlation Attention Based Correlation Module Correlation Transformer Nonlinear Correlation

May 18, 2024

GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing
Chengqing Yu, Fei Wang, Zezhi Shao, Tangwen Qian, Zhao Zhang, Wei Wei, Yongjun Xu
Time Series Forecasting Temporal Dependency Multivariate Time Series Forecasting Temporal Graph Neural Network Variable Model

May 14, 2024

DGCformer: Deep Graph Clustering Transformer for Multivariate Time Series Forecasting
Qinshuo Liu, Yanwen Fang, Pengtao Jiang, Guodong Li
Supervised Autoencoder Multivariate Time Series Forecasting Deep Graph Clustering

April 29, 2024

CVTN: Cross Variable and Temporal Integration for Time Series Forecasting
Han Zhou, Yuntian Chen
Time Series Forecasting Multivariate Time Series Forecasting Time Series Prediction Cross Inferential Network

April 22, 2024

SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
Lu Han, Xu-Yang Chen, Han-Jia Ye, De-Chuan Zhan
Hybrid Fusion Multivariate Time Series Forecasting Channel Correlation

April 7, 2024

Some variation of COBRA in sequential learning setup
Aryan Bhambu, Arabin Kumar Dey
Human Prediction Multivariate Time Series Forecasting Category Wise Variation Bayesian Optimisation System Configuration Short Term Load Forecasting Original CoBRA Structured Regression

March 29, 2024

TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods
Xiangfei Qiu, Jilin Hu, Lekui Zhou, Xingjian Wu, Junyang Du, Buang Zhang, Chenjuan Guo, Aoying Zhou, Christian S. Jensen, Zhenli Sheng, Bin Yang
Time Series Forecasting Multivariate Time Series Forecasting Univariate Time Series Forecasting Forecasting Method Fairness Benchmark Time Series Forecasting Method

March 14, 2024

MCformer: Multivariate Time Series Forecasting with Mixed-Channels Transformer
Wenyong Han, Tao Zhu Member, Liming Chen, Huansheng Ning, Yang Luo, Yaping Wan
Multivariate Time Series Forecasting Channel Wise Channel Correlation Frequency Aware Transformer

March 5, 2024

InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecasting
Ce Chi, Xing Wang, Kexin Yang, Zhiyan Song, Di Jin, Lin Zhu, Chao Deng, Junlan Feng
Transformer Based Multivariate Time Series Forecasting Long Term Time Series Forecasting Global Mixing Channel Mixing

March 4, 2024

CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables
Jiecheng Lu, Xu Han, Yan Sun, Shihao Yang
Multivariate Time Series Forecasting Synthetic Time Series Auxiliary Data Exogenous Variable Multivariate Model

March 1, 2024

Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling
Shiyi Qi, Liangjian Wen, Yiduo Li, Yuanhang Yang, Zhe Li, Zhongwen Rao, Lujia Pan, Zenglin Xu
Multivariate Time Series Forecasting Temporal Correlation Temporal Modeling Feature Decorrelation Channel Mixing

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

Multivariate Time Series Forecasting

Papers

DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting

CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecasting

UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting

TwinS: Revisiting Non-Stationarity in Multivariate Time Series Forecasting

TimeCMA: Towards LLM-Empowered Time Series Forecasting via Cross-Modality Alignment

ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks

MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs

Interpretable Multivariate Time Series Forecasting Using Neural Fourier Transform

VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting

GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing

DGCformer: Deep Graph Clustering Transformer for Multivariate Time Series Forecasting

CVTN: Cross Variable and Temporal Integration for Time Series Forecasting

SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion

Some variation of COBRA in sequential learning setup

TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods

MCformer: Multivariate Time Series Forecasting with Mixed-Channels Transformer

InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecasting

CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables

Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling

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