计算机应用 ›› 2020, Vol. 40 ›› Issue (10): 2795-2803.DOI: 10.11772/j.issn.1001-9081.2020040569

• 人工智能 • 上一篇    下一篇

基于多维社交关系嵌入的深层图神经网络推荐方法

何昊晨, 张丹红   

  1. 武汉理工大学 自动化学院, 武汉 430070
  • 收稿日期:2020-05-04 修回日期:2020-07-10 出版日期:2020-10-10 发布日期:2020-07-20
  • 通讯作者: 张丹红
  • 作者简介:何昊晨(1999-),男,湖北武汉人,主要研究方向:机器学习;张丹红(1968-),女,湖北汉川人,教授,硕士,主要研究方向:模式识别、智能系统。
  • 基金资助:
    国家自然科学基金资助项目(61876219)。

Recommendation method based on multidimensional social relationship embedded deep graph neural network

HE Haochen, ZHANG Danhong   

  1. School of Automation, Wuhan University of Technology, Wuhan Hubei 430070, China
  • Received:2020-05-04 Revised:2020-07-10 Online:2020-10-10 Published:2020-07-20
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61876219).

摘要: 社会化推荐系统通过用户的社会属性信息能缓解推荐系统中数据稀疏性和冷启动问题,从而提高推荐系统的精度。然而大多数社会化推荐方法主要针对单一的社交网络,或对多个社交网络进行线性叠加,使得用户社会属性难以充分参与计算,因而推荐的精度有限。针对该问题,提出一种多重网络嵌入的图形神经网络模型来实现复杂多维社交网络下的推荐,该模型构建了统一的方法来融合用户-物品、用户-用户等各种关系构成的多维复杂网络,通过注意力机制聚合不同类型的多邻居对节点生成作出贡献,并将多个图神经网络进行组合,从而构建了多维社交关系下的图神经网络推荐框架。这种方法通过拓扑结构直接反映推荐系统中实体及其相互间关系,直接在图上对相关信息进行不断更新计算,具有很强的归纳性,有效避免了传统推荐方法中信息利用不完全的问题。通过与相关的社会推荐算法进行比较,实验结果表明,所提方法在均方根误差(RMSE)和平均绝对误差(MAE)等推荐精度指标上有所改善,甚至在数据稀疏情况下也有良好的精度。

关键词: 多维社交网络, 社交化推荐, 图神经网络, 多层感知机, 网络嵌入

Abstract: The social recommendation system can alleviate the data sparsity and cold start problems in the recommendation system through the users' social attribute information, thereby improving the accuracy of the recommendation system. However, most social recommendation methods mainly aim at the single social network or linearly superimpose multiple social networks, making it difficult for the users' social attributes to fully participate in the calculation, so the accuracy of recommendation is limited. To solve this problem, a multi-network embedded graph neural network model was proposed to implement the recommendation in complex multidimensional social networks. In the model, a unified method was built to fuse the multidimensional complex networks composed of user-item, user-user and other relationships. Different types of multi-neighbors were aggregated to attribute to the node generation through attention mechanism, and multiple graph neural networks were combined to construct a graph neural network recommendation framework under multidimensional social relationships. In the proposed method, the entities in the recommendation system and their relationships were reflected by the topology structure, and the relevant information was calculated and updated continuously on the graph directly. It can be seen that the method is inductive, and avoids the problem of incomplete information utilization in traditional recommendation methods effectively. By comparing with related social recommendation algorithms, the experimental results show that the recommendation accuracy indicators such as Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of the proposed method are improved, and the method even has good accuracy on sparse data.

Key words: multi-dimensional social network, social recommendation, graph neural network, multi-layer perceptron, network embedding

中图分类号: