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