Robust Meta-Graph Learning: Exploring Multilevel Feature Interrelationships to Enhance Multimodal Time Series Prediction

This archive is distributed in association with the INFORMS Journal on Computing under the MIT License.

The software and data in this repository are a snapshot of the software and data that were used in the research reported on in the paper Robust Meta-Graph Learning: Exploring Multilevel Feature Interrelationships to Enhance Multimodal Time Series Prediction by Zongxi Liu, Gang Chen, Shuaiyong Xiao, and Huimin Zhao.

Cite

To cite the contents of this repository, please cite both the paper and this repo, using their respective DOIs.

https://doi.org/10.1287/ijoc.2024.0933

https://doi.org/10.1287/ijoc.2024.0933.cd

Below is the BibTex for citing this snapshot of the repository.

@misc{Liu2026,
  author =        {Liu, Zongxi and Chen, Gang and Xiao, Shuaiyong and Zhao, Huimin},
  publisher =     {INFORMS Journal on Computing},
  title =         {{Robust Meta-Graph Learning: Exploring Multilevel Feature Interrelationships to Enhance Multimodal Time Series Prediction}},
  year =          {2026},
  doi =           {10.1287/ijoc.2024.0933.cd},
  url =           {https://github.com/INFORMSJoC/2024.0933},
  note =          {Available for download at https://github.com/INFORMSJoC/2024.0933},
}  

Data

The public datasets can be obtained from the following repositories:

• The public dataset for the CH-SIMS case can be obtained from the repository: https://github.com/thuiar/MMSA
• The public dataset for the UR-FUNNY case can be obtained from the repository: https://github.com/ROC-HCI/UR-FUNNY
• The public dataset for the MIntRec2.0 case can be obtained from the repository: https://github.com/thuiar/MIntRec2.0

Replication

Install required packages (command: pip install).

pip install requirements.txt

Instantiate the model for each dataset.

The definition of RMGL model is provided in scripts/RMGL_Method.py (RMGL_model).