https://github.com/JiachengLi1995/TiSASRec

TensorFlow implementation for paper Time Interval Aware Self-Attention for Sequential Recommendation.
https://github.com/JiachengLi1995/TiSASRec

Last synced: about 2 months ago
JSON representation

TensorFlow implementation for paper Time Interval Aware Self-Attention for Sequential Recommendation.

• Host: GitHub
• URL: https://github.com/JiachengLi1995/TiSASRec
• Owner: JiachengLi1995
• Created: 2020-03-07T20:56:44.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2020-10-06T19:49:58.000Z (over 4 years ago)
• Last Synced: 2024-08-09T13:18:33.328Z (5 months ago)
• Language: Python
• Homepage:
• Size: 6.68 MB
• Stars: 118
• Watchers: 1
• Forks: 25
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• StarryDivineSky - JiachengLi1995/TiSASRec - Attention for Sequential Recommendation 时间间隔自注意力模型用于序列推荐。 基于序列模型框架对行为的时间戳进行建模，在下一个商品预测中探索不同时间间隔的影响。 (其他_推荐系统 / 网络服务_其他)

README

        
# TiSASRec: Time Interval Aware Self-Attention for Sequential Recommendation

This is our TensorFlow implementation for the paper:

Jiacheng Li, Yujie Wang, [Julian McAuley](http://cseweb.ucsd.edu/~jmcauley/) (2020). *[Time Interval Aware Self-Attention for Sequential Recommendation.](https://cseweb.ucsd.edu/~jmcauley/pdfs/wsdm20b.pdf)* WSDM'20

We refer to the repo [SASRec](https://github.com/kang205/SASRec).

Please cite our paper if you use the code or datasets.

The code is tested under a Linux desktop (w/ GTX 1080 Ti GPU) with TensorFlow.

For Pytorch version of TiSASRec, please refer to [repo](https://github.com/pmixer/TiSASRec.pytorch).

## Datasets

This repo includes ml-1m dataset as an example.

For Amazon dataset, you could download Amazon review data from *[here.](http://jmcauley.ucsd.edu/data/amazon/index.html)*.

## Model Training

To train our model on `ml-1m` (with default hyper-parameters): 

```

python main.py --dataset=ml-1m --train_dir=default 

```

## Misc

The implemention of self attention is modified based on *[this](https://github.com/Kyubyong/transformer)*.

## Contact

If you have any questions, please send me an email ([email protected]).