Corpus ID: 221819497

Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect

@article{Zeng2020KnowledgeTV,
  title={Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect},
  author={Zheni Zeng and Chaojun Xiao and Y. Yao and Ruobing Xie and Zhiyuan Liu and Fen Lin and Leyu Lin and M. Sun},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.09226}
}
  • Zheni Zeng, Chaojun Xiao, +5 authors M. Sun
  • Published 2020
  • Computer Science
  • ArXiv
  • Recommender systems aim to provide item recommendations for users, and are usually faced with data sparsity problem (e.g., cold start) in real-world scenarios. Recently pre-trained models have shown their effectiveness in knowledge transfer between domains and tasks, which can potentially alleviate the data sparsity problem in recommender systems. In this survey, we first provide a review of recommender systems with pre-training. In addition, we show the benefits of pre-training to recommender… CONTINUE READING
    1 Citations

    Figures and Tables from this paper

    UPRec: User-Aware Pre-training for Recommender Systems
    • PDF

    References

    SHOWING 1-10 OF 79 REFERENCES
    A survey on solving cold start problem in recommender systems
    • J. Gope, S. Jain
    • Computer Science
    • 2017 International Conference on Computing, Communication and Automation (ICCCA)
    • 2017
    • 19
    Deep Modeling of Social Relations for Recommendation
    • 19
    • PDF
    Boosting Recommender Systems with Advanced Embedding Models
    • 2
    A Survey on Knowledge Graph-Based Recommender Systems
    • 20
    • PDF
    MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation
    • 26
    • PDF
    Exploiting Pre-Trained Network Embeddings for Recommendations in Social Networks
    • 18
    Cross-Domain Recommender Systems
    • 139
    • PDF
    Recommender systems with social regularization
    • 1,232
    • PDF