In this repository, we release our implementations of existing representative group recommendation models.
- Aggregation method: AGREE
- Hyper-graph Learning: HyperGroup, HCR, HHGR
- Hyper-cude Learning: CubeRec
- Self-supervised Learning: GroupIM, HHGR, CubeRec
Besides, our ConsRec published in WWW'2023 is released here.
Below is the detailed information of our (re)implementation.
| Name | Title | Information | Comment |
|---|---|---|---|
| AGREE | Attentive Group Recommendation | SIGIR'2018 | Refactor |
| GroupIM | GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation | SIGIR'2020 | Refactor |
| HyperGroup | Hierarchical Hyperedge Embedding-based Representation Learning for Group Recommendation | TOIS'2021 | Implementation |
| HCR | Hypergraph Convolutional Network for Group Recommendation | ICDM'2021 | Official Codes |
| HHGR | Double-Scale Self-supervised Hypergraph Learning for Group Recommendation | CIKM'2021 | Refactor |
| CubeRec | Thinking inside The Box: Learning Hypercube Representations for Group Recommendation | SIGIR'2022 | Refactor |
Refactorrefers to refactor their official codes to tailor our experimental settings or datasets.
We thank the released official codes of existing baselines: AGREE, GroupIM, HCR, HHGR, and CubeRec.
If you make advantages of this repository in your research, please cite the following in your manuscript:
@inproceedings{wu2023consrec,
title={ConsRec: Learning Consensus Behind Interactions for Group Recommendation},
author={Wu, Xixi and Xiong, Yun and Zhang, Yao and Jiao, Yizhu and Zhang, Jiawei and Zhu, Yangyong and Philip S. Yu},
booktitle={Proceedings of the ACM Web Conference 2023},
year={2023},
organization={ACM}
}