https://github.com/netease-media/fparec
Official code for "Learning Positional Attention for Sequential Recommendation"
https://github.com/netease-media/fparec
Last synced: about 2 months ago
JSON representation
Official code for "Learning Positional Attention for Sequential Recommendation"
- Host: GitHub
- URL: https://github.com/netease-media/fparec
- Owner: NetEase-Media
- Created: 2024-11-15T10:23:03.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-11-15T10:25:20.000Z (6 months ago)
- Last Synced: 2025-02-02T05:42:46.748Z (4 months ago)
- Language: Python
- Size: 2.33 MB
- Stars: 1
- Watchers: 4
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Learning Positional Attention for Sequential Recommendation
This is our TensorFlow implementation for the paper:
*Learning Positional Attention for Sequential Recommendation*
Link: https://arxiv.org/abs/2407.02793
Please cite our paper if you use the code.
## Datasets
The preprocessed datasets are included in the repo (`e.g. data/ml-1m.txt`), where each line contains an `user id` and
`item id` (starting from 1) meaning an interaction (sorted by timestamp).
## Model Training
To train our model FPARec on `ml-1m` with default hyper-parameters:
```
bash scripts/train_fpa.sh
```
To train our model PARec on `ml-1m` with default hyper-parameters:
```
bash scripts/train_pa.sh
```
## Acknowledgement
Our code is developed based on [SASRec](https://github.com/kang205/SASRec/tree/master)*