PyTorch implementation of "STAIR: Manipulating Collaborative and Multimodal Information for E-Commerce Recommendation". (arXiv)
Requirements: Python >= 3.9 | PyTorch >=2.0 | TorchData >=0.6.0 | PyG >=2.3
conda create -n stair python=3.9;conda activate stair;bash env.sh
All datasets used in this project can be accessed via Google Drive.
cd STAIR
python main.py --config configs/Amazon2014Baby_550_MMRec.yaml
If you find STAIR useful in your research, please kindly cite:
@article{xu2024stair,
title={STAIR: Manipulating Collaborative and Multimodal Information for E-Commerce Recommendation},
author={Xu, Cong and He, Yunhang and Wang, Jun and Zhang, Wei},
journal={arXiv preprint arXiv:2412.11729},
year={2024}
}