Awesome
If you use the code in your project, please cite the following paper:
IEEE Big Data'22 (PDF)
@inproceedings{jeong2022nothing,
title={Nothing stands alone: Relational fake news detection with hypergraph neural networks},
author={Jeong, Ujun and Ding, Kaize and Cheng, Lu and Guo, Ruocheng and Shu, Kai and Liu, Huan},
booktitle={2022 IEEE International Conference on Big Data (Big Data)},
pages={596--605},
year={2022},
organization={IEEE}
}
Setups
- Create environment using Conda : We use following command to make conda env on Ubuntu 20.04 using Conda with python 3.7.6
conda create --name HGFND python==3.7.6
source activate HGFND
- Pytorch Installation on Conda : We use following command to install pytorch based on CUDA 10.2 for nvidia driver (Please check your CUDA version by <code>nvcc --version</code> before the installation)
conda install pytorch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 cudatoolkit=10.2 -c Pytorch
- PyG Installation on Conda : We use Pytorch 1.9.0 Linux Conda CUDA 10.2
conda install pyg -c pyg
- Install Dependencies using <code> pip install -r requirements.txt </code>
Usage
- Run the code with following commandline/parameters
python main.py --dataset politifact
Trouble Shooting
- Please apply <code>pip uninstall torch_spline_conv</code> if you encounter the following error:
OSError: /lib64/libm.so.6: version `GLIBC_2.27' not found
- Please refer to PyG FAQ for any types of error caused by PyG.
Dataset
- The UPFD dataset will be automatically downloaded to <code> data/{dataset-name}/raw/</code> when runnig <code> main.py </code>
- You can also manually download the dataset from UPFD github