https://github.com/edisonleeeee/graphssm
[NeurIPS 2024] State Space Models on Temporal Graphs: A First-Principles Study
https://github.com/edisonleeeee/graphssm
state-space-model temporal-graph-learning temporal-graphs
Last synced: 9 months ago
JSON representation
[NeurIPS 2024] State Space Models on Temporal Graphs: A First-Principles Study
- Host: GitHub
- URL: https://github.com/edisonleeeee/graphssm
- Owner: EdisonLeeeee
- Created: 2024-06-21T06:33:33.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2024-12-31T09:19:59.000Z (over 1 year ago)
- Last Synced: 2024-12-31T10:23:08.065Z (over 1 year ago)
- Topics: state-space-model, temporal-graph-learning, temporal-graphs
- Language: Python
- Homepage: https://arxiv.org/abs/2406.00943
- Size: 46.8 MB
- Stars: 8
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
🐍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
[](https://arxiv.org/abs/2406.00943)
## 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
```bib
@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}
}
```