Giter Site home page Giter Site logo

enoche / selfcf Goto Github PK

View Code? Open in Web Editor NEW
26.0 2.0 7.0 1.17 MB

Source code for "SelfCF: A Simple Framework for Self-supervised Collaborative Filtering". Accepted by ACM TORS.

License: MIT License

Python 100.00%
contrastive-learning graph-neural-networks recommender-system self-supervised-learning

selfcf's Introduction

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering (ACM TORS)

🏷️ Note: This repo. holds the best hyper-parameters for reproducibility of our models on Amazon-Grocery and Gourmet Food. Please note this repo. is deprecated and will not be maintained. SelfCF is integrated into ImRec.

  • 🔀 SelfCF is integrated into the unified ImRec framework.

This is our implementation of the paper:

Xin Zhou, Aixin Sun, Yong Liu, Jie Zhang, Chunyan Miao. SelfCF: A Simple Framework for Self-supervised Collaborative Filtering ACM

Overview

We present a simple framework that specialized for collaborative filtering problem. The framework enables learning of latent representations of users and items without Negative Samples.
We augment the output embeddings generated from backbone networks instead of the input user-item ids. For output embedding augmentation, we propose three techniques:

  • Historical embedding.
  • Embedding dropout.
  • Edge pruning.

For details, please refer to the paper.

Features

  • Standard data preprocessing.
  • Unified data splitting with global-timeline.
  • Standard evaluation protocols.
  • Posterior recommendation results.

Data

Download from Google Drive: Amazon-Vedio-Games/Food etc.

Environment:

python 3.6
pytorch 1.8
PyYAML 6.0
pandas 0.24
numpy 1.19

Please condier cite our paper:

@article{zhou2023selfcf,
  author = {Zhou, Xin and Sun, Aixin and Liu, Yong and Zhang, Jie and Miao, Chunyan},
  title = {SelfCF: A Simple Framework for Self-Supervised Collaborative Filtering},
  year = {2023},
  journal = {ACM Trans. Recomm. Syst.},
  publisher = {Association for Computing Machinery},
}

ACK:

We would like to give thanks to the following repos:
RecBole
BUIR

selfcf's People

Contributors

enoche avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

selfcf's Issues

Performance is not very good on Yelp2018

I tried this method on Yelp2018. The performance is not very good. Can the authors give some advices? May I know how many epochs it will usually take to reach convergence?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.