用于推荐系统的自监督超图Transformer 笔记

最新推荐文章于 2024-11-13 10:00:00 发布

原创

最新推荐文章于 2024-11-13 10:00:00 发布

· 1k 阅读

13 ·

版权

文章标签：

#笔记

本文提出了一种新颖的自监督超图Transformer框架SHT，通过探索用户间的全局协作关系，解决推荐系统中数据噪声和偏斜分布的问题。SHT通过超图神经网络保持用户和项目之间的全局协作效果，并利用跨视图生成式自我监督学习进行数据增强，提升推荐系统的鲁棒性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1 Title

Self-Supervised Hypergraph Transformer for Recommender Systems（Lianghao Xia, Chao Huang, Chuxu Zhang）【KDD 2022】

2 Conclusion

User behavior data in many practical recommendation scenarios is often noisy and exhibits skewed distribution, which may result in suboptimal representation performance in GNN-based
models. In this paper, we propose SHT, a novel Self-Supervised Hypergraph Transformer framework (SHT) which augments user representations by exploring the global collaborative relationships in an explicit way. Specifically, we first empower the graph neural CF paradigm to maintain global collaborative effects among users and items with a hypergraph transformer network. With the distilled global context, a cross-view generative self-supervised learning component is proposed for data augmentation over the user-item interaction graph, so as to enhance the robustness of recommender systems.