Home

Awesome

Awesome-SSLRec-Papers

Awesome

A collection of papers and resources about self-supervised learning (SSL) for recommendation (Rec).

Recommender systems personalize suggestions to combat information overload. Deep learning methods like RNNs, GNNs, and Transformers have improved these systems by understanding user behavior better. However, supervised learning struggles with data sparsity. Self-supervised learning (SSL) overcomes this by using inherent data structures for supervision, reducing dependence on labeled data. SSL-based recommender systems accurately predict and recommend, even with sparse data, by leveraging unlabeled data for meaningful representations.

<p align="center"> <img src="fig/taxonomy.png" alt="Framework" /> </p>

News

🤗 We're actively working on this project, and your interest is greatly appreciated! To keep up with the latest developments, please consider hit the STAR 🌟 and WATCH for updates.

Overview

This repository serves as a collection of recent advancements in employing self-supervised learning (SSL) across nine diverse recommendation scenarios, such as Collaborative Filtering, Sequential Recommendation, and more. We categorize and summarize the approaches based on three primary self-supervised frameworks: 1) Contrastive Learning, 2) Generative Learning, and 3) Adversarial Learning.

</p> </p> </p>

We hope this repository proves valuable to your research or practice in the field of self-supervised learning for recommendation systems. If you find it helpful, please consider citing our work:

@article{ren2024comprehensive,
  title={A Comprehensive Survey on Self-Supervised Learning for Recommendation},
  author={Ren, Xubin and Wei, Wei and Xia, Lianghao and Huang, Chao},
  journal={arXiv preprint arXiv:2404.03354},
  year={2024}
}

Table of Contents

Related Resources

🌐 General Collaborative Filtering

Contrastive Learning

Generative Learning

Adversarial Learning

🌐 Sequential Recommendation

Contrastive Learning

Generative Learning

Adversarial Learning

🌐 Social Recommendation

Contrastive Learning

Adversarial Learning

🌐 Knowledge-aware Recommendation

Contrastive Learning

Generative Learning

🌐 Cross-domain Recommendation

Contrastive Learning

Generative Learning

Adversarial Learning

🌐 Bundle Recommendation

Contrastive Learning

Generative Learning

🌐 Group Recommendation

Contrastive Learning

🌐 Multi-behavior Recommendation

Contrastive Learning

Generative Learning

🌐 Multi-modal Recommendation

Contrastive Learning

Generative Learning

Adversarial Learning

Contributing

If you have come across relevant resources, feel free to submit a pull request.

- (Journal/Confernce'20XX) **paper_name** [[paper](link)]

To add a paper to the survey, please consider providing more detailed information in the PR 😊

Contrastive Methods
  - View Creation (Data-based / Feature-based / Model-based)
  - Pair Sampling (Natural / Score-based)
  - Contrastive Objective (InfoNCE-based / JS-based / Explicit)
Generative Methods
  - Generative Learning Paradigm (Variational Autoencoding / Masked Autoencoding / Denoised Diffusion)
  - Generation Target
Adversarial Methods:
  - Adversarial Learning Paradigm (Differentiable / Non-Differentiable)
  - Adversarial Target
Please also consider providing a brief introduction about the method to help us quickly add the paper to our survey :)

Acknowledgements

The design of our README.md is inspired by Awesome-LLM-KG and Awesome-LLMs-in-Graph-tasks, thanks to their works!