MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation

Introduction

This is the Pytorch implementation for our MENTOR paper:

MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation

Environment Requirement

• python 3.9
• Pytorch 2.1.0

Dataset

We provide three processed datasets: Baby, Sports, Clothing.

Download from Google Drive: Baby/Sports/Clothing

Training

cd ./src
python main.py

Performance Comparison

Citing MENTOR

If you find MENTOR useful in your research, please consider citing our paper.

@inproceedings{xu2025mentor,
  title={Mentor: multi-level self-supervised learning for multimodal recommendation},
  author={Xu, Jinfeng and Chen, Zheyu and Yang, Shuo and Li, Jinze and Wang, Hewei and Ngai, Edith CH},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={39},
  number={12},
  pages={12908--12917},
  year={2025}
}

The code is released for academic research use only. For commercial use, please contact Jinfeng Xu.

Acknowledgement

The structure of this code is based on MMRec. Thank for their work.