ostwalt/graphhinge

Code for KDD'20 "An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph"

Heterogeneous INteract and aggreGatE (GraphHINGE)

This is a pytorch implementation of GraphHINGE model. This is the experiment code in the following work:

An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph
Jiarui Jin, Jiarui Qin, Yuchen Fang, Kounianhua Du, Weinan Zhang, Yong Yu, Zheng Zhang, Alexander J. Smola.
KDD 2020 Oral

and its extended work:

Learning Interaction Models of Structured Neighborhood on Heterogeneous Information Network
Jiarui Jin, Kounianhua Du, Weinan Zhang, Jiarui Qin, Yuchen Fang, Yong Yu, Zheng Zhang, Alexander J. Smola.
arXiv

Prerequisites

• Python 3.6
• Pytorch 1.8.0
• DGL 0.6.0

References

If you find this work helpful in your research, please consider citing the following paper. The bibtex are listed below:

@inproceedings{jin2020efficient,
  title={An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph},
  author={Jin, Jiarui and Qin, Jiarui and Fang, Yuchen and Du, Kounianhua and Zhang, Weinan and Yu, Yong and Zhang, Zheng and Smola, Alexander J},
  booktitle={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
  pages={75--84},
  year={2020}
}

@article{jin2020learning,
  title={Learning Interaction Models of Structured Neighborhood on Heterogeneous Information Network},
  author={Jin, Jiarui and Du, Kounianhua and Zhang, Weinan and Qin, Jiarui and Fang, Yuchen and Yu, Yong and Zhang, Zheng and Smola, Alexander J},
  journal={arXiv preprint arXiv:2011.12683},
  year={2020}
}