# MoHR: Recommendation Through Mixtures of Heterogeneous Item Relationships
This is our TensorFlow implementation for the paper:
[Wang-Cheng Kang](http://kwc-oliver.com/), [Mengting Wan](https://cseweb.ucsd.edu/~m5wan/), [Julian McAuley](https://cseweb.ucsd.edu/~jmcauley/) (2018). *[Recommendation Through Mixtures of Heterogeneous Item Relationships.](https://cseweb.ucsd.edu/~jmcauley/pdfs/cikm18b.pdf)* In Proceedings of ACM Conference on Information and Knowledge Management (CIKM'18)
Please cite our paper if you use the code or datasets.
The code is tested under a Linux desktop with TensorFlow 1.12.
## Datasets
The `Automotive` from Amazon is included in the repo. All datasets (after pre-processing) can be downloaded from:
- *[Amazon Automotive](http://cseweb.ucsd.edu/~wckang/MoHR/data/AutomotivePartitioned.npy)*
- *[Amazon Beauty](http://cseweb.ucsd.edu/~wckang/MoHR/data/BeautyPartitioned.npy)*
- *[Amazon Clothing](http://cseweb.ucsd.edu/~wckang/MoHR/data/ClothingPartitioned.npy)*
- *[Amazon Toys](http://cseweb.ucsd.edu/~wckang/MoHR/data/Toys_and_GamesPartitioned.npy)*
- *[Amazon Games](http://cseweb.ucsd.edu/~wckang/MoHR/data/Video_GamesPartitioned.npy)*
- *[Google Local](http://cseweb.ucsd.edu/~wckang/MoHR/data/GooglePartitioned.npy)*
- Steam (raw): [reviews](http://cseweb.ucsd.edu/~wckang/steam_reviews.json.gz), [game info](http://cseweb.ucsd.edu/~wckang/steam_games.json.gz) (see [here](https://github.com/kang205/SASRec) for more information)
## Model Training
A simple way to train our model is (with default hyper-parameters):
```
python main.py --dataset=Automotive
```
For the `Automotive` dataset, the model should be converged in 600 epochs, you should be able to see the test AUC in the log file reach 0.8.
For more details (e.g. learning rate, regularizations, etc), please refer to the code.
MoHR:通过混合异构项目关系进行推荐.zip
版权申诉
114 浏览量
2023-03-28
13:22:13
上传
评论
收藏 6.02MB ZIP 举报
快撑死的鱼
- 粉丝: 1w+
- 资源: 9154
最新资源
- index.jsp
- Screenshot_20240521_090410_com.huawei.android.launcher.jpg
- 单文件制作工具 7.0.2.3851-x86-x64
- Linux命令.xmind
- 基于Transformer实现的跨域Cross-view实时Map-view语义分割算法-附项目源码-优质项目实战.zip
- linux常用命令大全-.zip
- 2024彩虹聚合DNS管理系统源码 管理系统快速开发平台 聚合平台管理.zip
- elasticsearch介绍-.zip
- nodejs安装及环境配置-.zip
- 谷歌浏览器自动化测试版113.0.5672.0(包含linux,windows32/64,mac三个版本,不会自动更新)
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈