The official implementation for "EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning".

[2023.07.28] We release the pre-version of Pytorch-DGL for traffic forecasting.

[2023.07.10] We release the pre-version of Pytorch-DGL for link prediction.

Below we report the HR@50, NDCG@50 and NDCG@100 results on the above provided dataset.

Below we summarize the performance with regards to different metrics and horizons on the METR-LA dataset (see DCRNN).

• conf/: configurations for logging
• data/: dataset for model training and evaluation
• runme.sh: train or evaluate EasyDGL and baseline models
• src/: codes for model definition

Here are commands for training the model for link prediction and traffic forecasting respectively.

python src/demo_recsys.py --config conf/model/Netflix/EasyDGL.yaml

python src/demo_traffic.py --config conf/model/METR-LA/EasyDGL.yaml

If you find our codes useful, please consider citing our work

@inproceedings{chen2021learning,
  title={Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation},
  author={Chen, Chao and Geng, Haoyu and Yang, Nianzu and Yan, Junchi and Xue, Daiyue and Yu, Jianping and Yang, Xiaokang},
  booktitle={Proceedings of the International Conference on Machine Learning (ICML '21)},
  pages={1606--1616},
  year={2021},
  organization={PMLR}
}

@article{chen2023easydgl,
  title={EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning},
  author={Chen, Chao and Geng, Haoyu and Yang, Nianzu and Yang, Xiaokang and Yan, Junchi},
  journal={arXiv preprint arXiv:2303.12341},
  year={2023}
}