跳到主要导航 跳到搜索 跳到主要内容

Disentangled Hierarchical Attention Graph Neural Network for Recommendation

  • Beihang University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Heterogeneous information networks (HIN) have been widely used in recommendation systems, aiming to solve how to model complex interactions between entities and data sparsity issue. Due to the excellent performance of Graph Neural Networks (GNN) in representation learning, they are applied in recommendation systems based on HIN. However, most current works focusing on HIN overlook the entanglement of latent factors originating from different aspects. Besides, most of them use meta path-based methods, which fail to consider the semantic information among the paths. In this paper, we propose a Disentangled Hierarchical Attention Graph Neural Network for Recommendation (DHARec), which applies disentangled representations for nodes in HIN. Instead of relying solely on meta paths, we leverage one-hop semantic relation neighbors to aggregate representations based on hierarchical attention, including intra relation and inter relation attention. Specifically, intra relation attention is primarily used to learn the contribution of a neighbor within the same semantic relation, while inter relation attention focuses on learning the importance of different semantic relations and fusing representations from these relations with appropriate weights. Extensive experimental results on three HIN-based datasets demonstrate that our approach outperforms existing methods.

源语言英语
主期刊名Advanced Intelligent Computing Technology and Applications - 20th International Conference, ICIC 2024, Proceedings
编辑De-Shuang Huang, Qinhu Zhang, Xiankun Zhang
出版商Springer Science and Business Media Deutschland GmbH
415-426
页数12
ISBN(印刷版)9789819756629
DOI
出版状态已出版 - 2024
活动20th International Conference on Intelligent Computing, ICIC 2024 - Tianjin, 中国
期限: 5 8月 20248 8月 2024

出版系列

姓名Lecture Notes in Computer Science
14875 LNAI
ISSN(印刷版)0302-9743
ISSN(电子版)1611-3349

会议

会议20th International Conference on Intelligent Computing, ICIC 2024
国家/地区中国
Tianjin
时期5/08/248/08/24

指纹

探究 'Disentangled Hierarchical Attention Graph Neural Network for Recommendation' 的科研主题。它们共同构成独一无二的指纹。

引用此