Skip to content

jinkwan1115/ChannelTokenFormer

Repository files navigation

[ICLR 2026] ChannelTokenFormer

This repository is the official implementation of Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness.

Requirements

To install requirements:

pip install -r requirements.txt

Training

To train the model in the paper, run this command:

bash ./scripts_practical/ChannelTokenFormer/CTF_ETT1_practical.sh

These scripts include evaluation also.

Evaluation

To evaluate model on SolarWind-missing scenarios, you should first train and save a checkpoint with the practical setting, then run missing-scenario inference.

  1. Train with SolarWind practical setting and generate checkpoint files:
bash ./scripts_practical/ChannelTokenFormer/CTF_SW_practical.sh
  1. Confirm the saved checkpoint directory from the training output (or your configured checkpoints path).

  2. Set that checkpoint directory in the missing evaluation script/config, then run:

bash ./scripts_practical/ChannelTokenFormer/CTF_SW_missing.sh

CTF_SW_missing.sh requires a valid pretrained checkpoint path from Step 1.

Contributing

We appreciate the following GitHub repos a lot for their valuable code and efforts.

About

[ICLR 2026] Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors