LGMRec

LGMRec (AAAI'24)

This is the Pytorch implementation for our AAAI 2024 paper:

Zhiqiang Guo, Jianjun Li, Guohui Li, Chaoyang Wang, Si Shi, Bin Ruan. LGMRec: Local and Global Graph Learning for Multimodal Recommendation. In AAAI 2024. Paper

Notice: The results of the baseline MMGCN have been updated in our new version.

Overview

Environment

pip install -r requirements.txt

Data

Download from Google Drive: Baby/Sports/Clothing. The data contains text and image features extracted from Sentence-Transformers and VGG-16 and has been publiced in MMRec framework.

Run

1. Put your downloaded data (e.g. baby) under data/ dir.
2. Run train.sh to train LGMRec: bash train.sh You may specify other parameters in CMD or config with configs/model/*.yaml and configs/dataset/*.yaml.

Citation

@inproceedings{guo2024lgmrec,
author = {Zhiqiang Guo and Jianjun Li and Guohui Li and Chaoyang Wang and Si Shi and Bin Ruan},
title = {LGMRec: Local and Global Graph Learning for Multimodal Recommendation},
booktitle = {Proceedings of AAAI 2024},
pages = {8454-8462},
year = {2024}
}

The code has been integrated into the MMRec repository.