LOBSTER: Bilateral Global Semantic Enhancement for Multimedia Recommendation

Introduction

This is the Pytorch implementation for our LOBSTER paper:

LOBSTER: Bilateral Global Semantic Enhancement for Multimedia Recommendation

Environment Requirement

• python 3.9
• Pytorch 2.1.0

Dataset

We provide three processed datasets: Baby, Sports.

Download from Google Drive: Baby/Sports

Training

cd ./src
python main.py

Performance Comparison

Citing LOBSTER

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

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.