Framework adopted

We sincerely thank for the robust support provided by the SELFRec framework for this project.

SELFRec is a Python framework for self-supervised recommendation (SSR) which integrates commonly used datasets and metrics, and implements many state-of-the-art SSR models. SELFRec has a lightweight architecture and provides user-friendly interfaces. It can facilitate model implementation and evaluation. Founder and principal contributor: @Coder-Yu @xiaxin1998
Supported by: @AIhongzhi (A/Prof. Hongzhi Yin, UQ)

To learn more about the Self Rec framework, please visit https://github.com/Coder-Yu/SELFRec/.

Architecture

Requirements

numba==0.53.1
numpy==1.20.3
scipy==1.6.2
torch>=1.7.0

Usage

1. Configure the xx.conf file in the directory named conf. (xx is the name of the model you want to run)
2. Run main.py and choose the model you want to run.

Implemented Models

Related Datasets

Model	Paper	Type	Code
DSVC	Yang et al. Dual Social View Enhanced Contrastive Learning for Social Recommendation, TCSS'24.	Graph + CL	PyTorch

Datasets	Yelp2018	Douban-book	FilmTrust
# User	$45,919$	$13,025$	$1,509$
# Item	$45,538$	$22,348$	$2,072$
# Interaction	$1,183,610$	$598,420$	$35,497$
# Relation	$709,459$	$169,150$	$1,853$
U-I Density	$5.66\times10^{-4}$	$2.06\times10^{-3}$	$1.14\times10^{-2}$
U-U Density	$8.01\times10^{-4}$	$1.04\times10^{-3}$	$1.92\times10^{-3}$

Reference

If you find this repo helpful to your research, please cite our paper.

@article{yang2024dual,
  title={Dual Social View Enhanced Contrastive Learning for Social Recommendation},
  author={Yang, Shixiao and Qin, Zhida and Du, Enjun and Zhou, Pengzhan and Huang, Tianyu},
  journal={IEEE Transactions on Computational Social Systems},
  year={2024},
  publisher={IEEE}
}