计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (10): 148-155.DOI: 10.3778/j.issn.1002-8331.2301-0141

• 模式识别与人工智能 • 上一篇    下一篇

保留模体信息的属性二分图神经网络表示学习

吕少卿,王驰驰,李婷婷,包志强   

  1. 1.西安邮电大学 通信与信息工程学院,西安 710121
    2.西安邮电大学 陕西省信息通信网络及安全重点实验室,西安 710121
  • 出版日期:2024-05-15 发布日期:2024-05-15

Attributed Bipartite Graph Neural Networks with Motifs Information for Network Representation Learning

LYU Shaoqing, WANG Chichi, LI Tingting, BAO Zhiqiang   

  1. 1.School of Communications & Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an 710121, China
    2.Shaanxi Key Laboratory of Information Communication Network and Security, Xi’an University of Posts and Telecommunications, Xi’an 710121, China
  • Online:2024-05-15 Published:2024-05-15

摘要: 目前网络表示学习方法大多针对通过网络,忽略了属性二分网络的特殊性以及网络的模体信息等。为了解决以上问题,提出一种保留模体信息的属性二分图神经网络表示学习方法MABG。该方法首先通过网络中两节点共同参与形成的蝶形模体数量来调整边的权重,从而构建模体权重矩阵,获得包含模体信息的属性二分网络邻接矩阵。接着采取不同的策略捕捉网络中的显式和属性隐式消息,对于不同类型节点集合间的显式关系采用消息传递机制,对于同类型节点中的隐式关系采用消息对齐机制,同时使用对抗模型最小化输入特征和显式关系表示之间的差异,之后通过级联框架来捕捉高阶信息并得到最终的节点表示。将该模型在四个真实公开的数据集上执行推荐任务并与其他方法进行对比,验证了该模型的有效性。

关键词: 属性二分网络, 网络表示学习, 网络模体, 图神经网络

Abstract: At present, network representation learning methods are mostly aimed at homogeneous networks, ignoring the particularity of attributed bipartite networks and the motifs structure of networks. In order to solve the above problems, this paper proposes an attributed bipartite graph neural network with motifs information for network representation learning (MABG). MABG adjusts the edge weights by the number of butterfly motifs formed by two nodes in the network, to construct the motifs weight matrix and obtain the attributed bipartite network adjacency matrix with motifs information. Then two different strategies are adopted to capture the explicit and implicit messages in the bipartite network. For explicit relationships, a message-passing mechanism is operated between different types of nodes. For implicit relationships, a message alignment mechanism is used in nodes of the same type. An adversarial model is implemented to minimize the difference between input attributes and explicit relationship representations. Finally, a cascaded framework is proposed to capture high-order network information and obtain the final node representation. Extensive experiments are conducted in recommended tasks on four real-world datasets. The results demonstrate the effectiveness of MABG compared with other state-of-art methods.

Key words: attributed bipartite network, network representation learning, network motifs, graph neural network