🐍GraphSSM (Graph State Space Models)

State Space Models on Temporal Graphs: A First-Principles Study

Jintang Li¹, Ruofan Wu², Boqun Ma³, Xinzhou Jin¹, Liang Chen¹, Zibin Zheng¹

¹Sun Yat-sen University, ²Coupang, ³Shanghai Jiao Tong University

Environments

Note

Higher versions should be also compatible.

conda create -n GraphSSM python=3.10
conda activate GraphSSM

pip install torch==2.2.2 torchvision==0.17.2 torchaudio==2.2.2 --index-url https://download.pytorch.org/whl/cu121
pip install torch_geometric
pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.2.0+cu121.html

pip install -r requirements.txt

Reproduction

bash scripts/s4.sh
bash scripts/s5.sh
bash scripts/s6.sh

Citation

If you find this repository useful in your research, please consider giving a star ⭐ and a citation

@inproceedings{graphssm,
  author       = {Jintang Li and
                  Ruofan Wu and
                  Xinzhou Jin and
                  Boqun Ma and
                  Liang Chen and
                  Zibin Zheng},
  title        = {State Space Models on Temporal Graphs: {A} First-Principles Study},
  booktitle    = {NeurIPS},
  year         = {2024}
}