https://github.com/pmixer/sasrec.pytorch

PyTorch(1.6+) implementation of https://github.com/kang205/SASRec
https://github.com/pmixer/sasrec.pytorch

pytorch recommender-system sasrec sequential-models

Last synced: 3 days ago
JSON representation

PyTorch(1.6+) implementation of https://github.com/kang205/SASRec

• Host: GitHub
• URL: https://github.com/pmixer/sasrec.pytorch
• Owner: pmixer
• License: apache-2.0
• Created: 2020-09-11T01:08:32.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2024-10-14T09:02:19.000Z (about 1 month ago)
• Last Synced: 2024-11-05T13:43:03.289Z (8 days ago)
• Topics: pytorch, recommender-system, sasrec, sequential-models
• Language: Python
• Homepage:
• Size: 19.8 MB
• Stars: 350
• Watchers: 5
• Forks: 93
• Open Issues: 28
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
modified based on [paper author's tensorflow implementation](https://github.com/kang205/SASRec), switching to PyTorch(v1.6) for simplicity, fixed issues like positional embedding usage etc. (making it harder to overfit, except for that, in recsys, personalization=overfitting sometimes)

to train:

```

python main.py --dataset=ml-1m --train_dir=default --maxlen=200 --dropout_rate=0.2 --device=cuda

```

just inference:

```

python main.py --device=cuda --dataset=ml-1m --train_dir=default --state_dict_path='ml-1m_default/SASRec.epoch=1000.lr=0.001.layer=2.head=1.hidden=50.maxlen=200.pth' --inference_only=true --maxlen=200

```

output for each run would be slightly random, as negative samples are randomly sampled, here's my output for two consecutive runs:

```

1st run - test (NDCG@10: 0.5897, HR@10: 0.8190)

2nd run - test (NDCG@10: 0.5918, HR@10: 0.8225)

```

pls check paper author's [repo](https://github.com/kang205/SASRec) for detailed intro and more complete README, and here's the paper bib FYI :)

```

@inproceedings{kang2018self,

  title={Self-attentive sequential recommendation},

  author={Kang, Wang-Cheng and McAuley, Julian},

  booktitle={2018 IEEE International Conference on Data Mining (ICDM)},

  pages={197--206},

  year={2018},

  organization={IEEE}

}

```

I see a dozen of citations of the repo recently🫰, here's the repo bib if needed.

```

@software{Huang_SASRec_pytorch,

author = {Huang, Zan},

title = {PyTorch implementation for SASRec},

url = {https://github.com/pmixer/SASRec.pytorch},

year={2020}

}

```