Skip to content

Latest commit

 

History

12 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 

Repository files navigation

A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective

PRs Welcome Stars

image-20250212190349685

  • A channel strategy refers to the approach employed to process, integrate, or utilize information from multiple input channels.
  • Channel Independence (CI): The CI strategy treats each channel independently, without considering any potential interactions or correlations among channels. Each channel is processed as a separate input, and no shared information or dependencies are utilized.
  • Channel Dependence (CD): The CD strategy assumes that all channels in a multivariate time series are inherently correlated and interdependent, treating them as a unified entity during the forecasting process.
  • Channel Partiality (CP): The CP strategy strikes a balance between CI and CD, allowing each channel to retain a degree of independence while simultaneously interacting with other related channels. This approach emphasizes a hybrid state where channels selectively interact and exhibit partial correlations.

This repository contains a list of papers and their corresponding codebases, categorized by CI, CD, and CP.

Strategy Mechanism Asym. Lag. Pol. Gw. Dyn. Ms. Method Paradigm Venue Year Code
CI - - - - - - - PatchTST Specific ICLR 2023 Link
CI - - - - - - - CycleNet Specific NIPS 2024 Link
CI - - - - - - - DLinear Specific AAAI 2023 Link
CI - - - - - - - One-Fits-All Foundation ICML 2024 Link
CI - - - - - - - Timer Foundation NIPS 2023 Link
CI - - - - - - - S2IP-LLM Foundation ICML 2024 Link
CI - - - - - - - TEMPO Foundation ICML 2024 Link
CI - - - - - - - LLM4TS Foundation NIPS 2023 Link
CI - - - - - - - Time-LLM Foundation ICLR 2024 Link
CI - - - - - - - RevIN Plugin ICLR 2021 Link
CD CNN-based ✓ - - - - - Informer Specific AAAI 2021 Link
CD CNN-based ✓ - - - - - Autoformer Specific NIPS 2021 Link
CD CNN-based ✓ - - - - - FEDformer Specific ICML 2022 Link
CD CNN-based ✓ - - - - - TimesNet Specific ICLR 2023 Link
CD MLP-based ✓ - - - - - TSMixer Specific KDD 2023 Link
CD MLP-based ✓ - - - - - TTM Foundation NIPS 2024 Link
CD Transformer-based ✓ - - - ✓ - iTransformer Specific ICLR 2024 Link
CD Transformer-based ✓ - - - ✓ - Crossformer Specific ICLR 2023 Link
CD Transformer-based ✓ ✓ - - - - VCformer Specific IJCAI 2024 Link
CD Transformer-based ✓ ✓ - - ✓ - MOIRAI Foundation ICML 2024 Link
CD Transformer-based ✓ - - - ✓ - UniTS Foundation NIPS 2024 Link
CD Transformer-based ✓ - - - ✓ - TQNet Specific ICML 2025 Link
CD GNN-based - - - - ✓ - GTS Specific ICLR 2021 Link
CD GNN-based ✓ - - - - ✓ MSGNet Specific AAAI 2024 Link
CD GNN-based - ✓ - - - - FourierGNN Specific NIPS 2023 Link
CD GNN-based - ✓ - - - - FC-STGNN Specific AAAI 2024 Link
CD GNN-based ✓ - - - ✓ - TPGNN Specific NIPS 2022 Link
CD GNN-based ✓ - - - ✓ ✓ ESG Specific KDD 2022 Link
CD GNN-based ✓ - - - ✓ ✓ EnhanceNet Plugin ICDE 2021 Link
CD Others ✓ ✓ - - - - SOFTS Specific NIPS 2024 Link
CD Others ✓ - - ✓ - - C-LoRA Plugin CIKM 2024 Link
CP CNN-based ✓ - - - - - ModernTCN Specific ICLR 2024 Link
CP Transformer-based ✓ - - ✓ - - DUET Specific KDD 2025 Link
CP Transformer-based ✓ - - - ✓ - MCformer Specific IITJ* 2024 -
CP Transformer-based ✓ - - ✓ ✓ - DGCformer Specific arXiv 2024 -
CP Transformer-based - - - - ✓ - CM Plugin NIPS 2024 -
CP GNN-based ✓ - - - ✓ - MTGNN Specific KDD 2020 Link
CP GNN-based ✓ - - ✓ - - CrossGNN Specific NIPS 2023 Link
CP GNN-based ✓ - - - ✓ - WaveForM Specific AAAI 2023 Link
CP GNN-based - - - - ✓ - MTSF-DG Specific VLDB 2023 Link
CP GNN-based ✓ - - ✓ ✓ ✓ ReMo Specific IJCAI 2023 -
CP GNN-based ✓ - - - ✓ ✓ Ada-MSHyper Specific NIPS 2024 Link
CP GNN-based - ✓ - ✓ ✓ - TimeFilter Specific ICML 2025 Link
CP Others ✓ ✓ - - ✓ - LIFT Plugin ICLR 2024 Link
CP Others ✓ - - ✓ - - CCM Plugin NIPS 2024 Link

About

[IJCAI 2026] A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective

Resources

Stars

49 stars

Watchers

2 watching

Forks

Releases

Packages

Contributors