• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学 ›› 2023, Vol. 45 ›› Issue (07): 1300-1307.

• 人工智能与数据挖掘 • 上一篇    下一篇

基于增强偏好影响力的图注意力网络推荐算法

高玮蔚1,刘杨2,马慧芳1,唐月晨1   

  1. (1.西北师范大学计算机科学与工程学院,甘肃 兰州 730070;2.中国交通信息科技集团有限公司,北京 101399)
  • 收稿日期:2021-09-26 修回日期:2022-03-03 接受日期:2023-07-25 出版日期:2023-07-25 发布日期:2023-07-11
  • 基金资助:
    国家自然科学基金(622760736,1762078,61363058);西北师范大学青年教师能力提升计划(NWNU-LKQN2019-2);甘肃省自然科学基金(21JR7RA114);甘肃省高校产业支撑项目(2022CYZC-11)

Graph attention network with enhanced preference influence for recommendation

GAO Wei-wei1,LIU Yang2,MA Hui-fang1,TANG Yue-chen1   

  1. (1.College of Computer Science and Engineering,Northwest Normal University,Lanzhou 730070;
    2.China Communications Information Technology Group Co.,Ltd.,Beijing 101399,China)
  • Received:2021-09-26 Revised:2022-03-03 Accepted:2023-07-25 Online:2023-07-25 Published:2023-07-11

摘要: 图神经网络能够有效地挖掘用户与项目复杂的交互行为,通过捕获图中节点的高阶信息提升推荐效果。提出一种基于增强偏好影响力的图注意力网络推荐算法,该算法利用图注意力网络融合偏好影响力,进而捕获用户与项目交互之间的潜在信息。具体地,首先构建用户-项目交互二部图,设计注意力邻域聚合策略在图结构上自适应地学习用户与项目的表示;其次,设计了偏好影响增强层,强化相似用户(项目)的偏好对目标用户(项目)的影响;最后,将相似用户(项目)对目标用户(项目)的偏好影响与目标用户(项目)的表示耦合,利用多层感知机得到用户-项目交互的可能性分数。在2个真实数据集上的实验结果验证了算法中注意力邻域聚合策略与偏好影响力的合理性与有效性。

关键词: 增强偏好, 图注意力网络, 推荐系统, 偏好影响力

Abstract: Graph neural network can effectively capture the complex interaction behavior between user and item in the recommendation scene. By capturing the higher-order information of nodes in the graph, recommendation performance can be improved. A Graph Attention Network with Enhanced preference influence for recommendation (GEPR) is proposed. The algorithm uses graph attention network to fuse preference influence, and then captures the potential information between user and item interaction. Specifically, the user-item bipartite graph is firstly constructed based on user-item interaction, and the attention neighborhood aggregation strategy is designed to learn the embedded representation of user and item adaptively on the graph structure. Secondly, a preference influence enhancement layer is designed to strengthen the influence of similar users(items)' preferences on target users(items)' preferences. Finally, multi-layer perceptron is used to obtain the probability score of user-item interaction by coupling the preference influence of similar users (items) on target users (items) with the embedding effect of target users (items). Experimental results on two real data sets verify the rationality and validity of the attention neighborhood aggregation strategy and preference influence in the proposed method.


Key words: enhanced preference;graph attention network;recommendation , system;preference influence