Paper of the source codes released:

Chunyuan Yuan, Jiacheng Li, Wei Zhou, Yijun Lu, Xiaodan Zhang, Songlin Hu. DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction. In ECML-PKDD 2020.

Dependencies:

Gensim==3.7.2

Jieba==0.39

Scikit-learn==0.21.2

Pytorch==1.1.0

Reproduce the experimental results:

1. create an empty directory: checkpoint/
2. run script run.py

Citation

If you find this code useful in your research, please cite our paper:

@inproceedings{dyhgcn_yuan_2020,
  title={DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction},
  author={Chunyuan Yuan, Jiacheng Li, Wei Zhou, Yijun Lu, Xiaodan Zhang, Songlin Hu},
  booktitle={Joint European Conference on Machine Learning and Knowledge Discovery in Databases},
  year={2020},
  organization={Springer}
}