Skip to content


Folders and files

Last commit message
Last commit date

Latest commit



5 Commits

Repository files navigation



This is the code for the ACM Multimedia 2021 Paper: Mining Latent Structures for Multimedia Recommendation.


Dataset Preparation

  • Download 5-core reviews data, meta data, and image features from Amazon product dataset. Put data into the directory data/meta-data/.

  • Install sentence-transformers and download pretrained models to extract textual features. Unzip pretrained model into the directory sentence-transformers/:

    ├─ data/: 
        ├── sports/
        	├── meta-data/
        		├── image_features_Sports_and_Outdoors.b
        		├── meta-Sports_and_Outdoors.json.gz
        		├── reviews_Sports_and_Outdoors_5.json.gz
        ├── sentence-transformers/
            	├── stsb-roberta-large
  • Run python to preprocess data.

  • Run python to build cold-start data.

  • We provide processed data Baidu Yun (access code: m37q), Google Drive.

Quick Start

Start training and inference as:

cd codes
python --dataset {DATASET}

For cold-start settings:

python --dataset {DATASET} --core 0 --verbose 1 --lr 1e-5


  • Python 3.6
  • torch==1.5.0
  • scikit-learn==0.24.2


Please cite our paper if you use the code:

  title     = {Mining Latent Structures for Multimedia Recommendation},
  author    = {Zhang, Jinghao and 
               Zhu, Yanqiao and 
               Liu, Qiang and
               Wu, Shu and 
               Wang, Shuhui and 
               Wang, Liang},
  booktitle = {Proceedings of the 29th ACM International Conference on Multimedia},
  pages     = {3872–3880},
  year      = {2021}


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