EUVIMEDEUVIMED entdecken
Crossref

A Multi-strategy-based Pre-training Method for Cold-start Recommendation

Bowen Hao, Hongzhi Yin, Jing Zhang, Cuiping Li, Hong Chen

ACM Transactions on Information Systems · 30.04.2023 · 41 (2) · 1-24

DOI: 10.1145/3544107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 25.01.2023. Verfasst von Bowen Hao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Key Research & Develop Plan, National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The cold-start issue is a fundamental challenge in Recommender Systems. The recent self-supervised learning (SSL) on Graph Neural Networks (GNNs) model, PT-GNN, pre-trains the GNN model to reconstruct the cold-start embeddings and has shown great potential for cold-start recommendation. However, due to the over-smoothing problem, PT-GNN can only capture up to 3-order relation, which cannot provide much useful auxiliary information to depict the target cold-start user or item. Besides, the embedding reconstruction task only considers the intra-correlations within the subgraph of users and items, while ignoring the inter-correlations across different subgraphs. To solve the above challenges, we propose a multi-strategy-based pre-training method for cold-start recommendation (MPT), which extends PT-GNN from the perspective of model architecture and pretext tasks to improve the cold-start recommendation performance. 1 Specifically, in terms of the model architecture, in addition to the short-range dependencies of users and items captured by the GNN encoder, we introduce a Transformer encoder to capture long-range dependencies. In terms of the pretext task, in addition to considering the intra-correlations of users and items by the embedding reconstruction task, we add an embedding contrastive learning task to capture inter-correlations of users and items. We train the GNN and Transformer encoders on these pretext tasks under the meta-learning setting to simulate the real cold-start scenario, making the model able to be easily and rapidly adapted to new cold-start users and items. Experiments on three public recommendation datasets show the superiority of the proposed MPT model against the vanilla GNN models, the pre-training GNN model on user/item embedding inference, and the recommendation task.

Förderung

  • National Key Research & Develop Plan
  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Australian Research Council Future Fellowship
  • Discovery Project

Zitieren

APA

Hao, B., Yin, H., Zhang, J., Li, C., & Chen, H. (2023). A Multi-strategy-based Pre-training Method for Cold-start Recommendation. ACM Transactions on Information Systems, 41(2), 1-24. https://doi.org/10.1145/3544107

Vancouver

Hao B, Yin H, Zhang J, Li C, Chen H. A Multi-strategy-based Pre-training Method for Cold-start Recommendation. ACM Transactions on Information Systems. 2023;41(2):1-24. doi:10.1145/3544107

BibTeX
@article{Hao2023,
  author = {Hao, Bowen and Yin, Hongzhi and Zhang, Jing and Li, Cuiping and Chen, Hong},
  title = {A Multi-strategy-based Pre-training Method for Cold-start Recommendation},
  journal = {ACM Transactions on Information Systems},
  year = {2023},
  volume = {41},
  number = {2},
  pages = {1--24},
  doi = {10.1145/3544107}
}
Kostenlos starten →