This repository is the official code for our IJCAI 2024 paper: "A Grassmannian Manifold Self-Attention Network for Signal Classification". GDLNet
If you have any problems, please don't hesitate to contact me.
To install the necessary dependencies by conda, run the following command:
conda env create -f GDLNet.yml
conda activate GDLNet
Please download the datasets and put them in the folder 'data'.
- MAMEM-SSVEP-II: https://www.mamem.eu/results/datasets/
- BCI-ERN: https://www.kaggle.com/competitions/inria-bci-challenge/data
Link to download data
To train and test the experiments on the Mamem and Bcicha datasets, run this command:
python GDLNet_mamem.py
python GDLNet_baicha.py
@inproceedings{wang2024grassmannian,
title={A Grassmannian Manifold Self-Attention Network for Signal Classification},
author={Wang, Rui and Hu, Chen and Chen, Ziheng and Wu, Xiao-Jun and Song, Xiaoning},
booktitle={Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence},
pages={5099--5107},
year={2024}
}@inproceedings{pan2022matt,
title={MAtt: a manifold attention network for EEG decoding},
author={Pan, Yue-Ting and Chou, Jing-Lun and Wei, Chun-Shu},
booktitle={Advances in Neural Information Processing Systems},
volume={35},
pages={31116--31129},
year={2022}
}@inproceedings{hu2025ijcai,
title = {A Correlation Manifold Self-Attention Network for EEG Decoding},
author = {Hu, Chen and Wang, Rui and Song, Xiaoning and Zhou, Tao and Wu, Xiao-Jun and Sebe, Nicu and Chen, Ziheng},
booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-25}},
pages = {5372--5380},
year = {2025},
}