The implementation code will be released after the acceptance of the paper.
This is the PyTorch implementation for CIDF proposed in the paper Correlation-guided Information Deep Fusion for Multi-modal Recommendation.
Gang-Feng Ma, Xu-Hua Yang, Haixia Long, Xin-Li Xu, Xiao-Xin Li, Peng Jiang. 2024.
We develop our codes in the following environment:
- python==3.7.10
- numpy==1.19.2
- pandas==1.12.3
- scipy==1.6.0
- tqdm==4.59.0
- torch==1.8.1
Dataset | # User | # Items | # Interaction | Sparsity |
---|---|---|---|---|
Baby | 19,445 | 7,050 | 160,792 | 99.883% |
Sports | 35,598 | 18,357 | 296,337 | 99.955% |
Clothing | 39,387 | 23,033 | 278,677 | 99.969% |
run.sh