Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (10): 3260-3266.DOI: 10.11772/j.issn.1001-9081.2023101557

• The 40th CCF National Database Conference (NDBC 2023) • Previous Articles     Next Articles

Information diffusion prediction model of prototype-aware dual-channel graph convolutional neural network

Nengqiang XIANG, Xiaofei ZHU(), Zhaoze GAO   

  1. College of Computer Science and Engineering,Chongqing University of Technology,Chongqing 400054,China
  • Received:2023-11-13 Revised:2023-12-28 Accepted:2024-01-02 Online:2024-10-15 Published:2024-10-10
  • Contact: Xiaofei ZHU
  • About author:XIANG Nengqiang, born in 1998, M. S. candidate. His research interests include natural language processing, social network.
    GAO Zhaoze, born in 1996, M. S. candidate. His research interests include natural language processing, stance detection.
  • Supported by:
    Chongqing Natural Science Foundation CSTB2022NSCQ-MSX1672;Science and Technology Research Program Major Project of Chongqing Municipal Education Commission(KJZD-M202201102);Graduate Education High-quality Development Project of Chongqing University of Technology(gzlcx20233187)

原型感知双通道图卷积神经网络的信息传播预测模型

项能强, 朱小飞(), 高肇泽   

  1. 重庆理工大学 计算机科学与工程学院,重庆 400054
  • 通讯作者: 朱小飞
  • 作者简介:项能强(1998—),男,四川达州人,硕士研究生,CCF会员,主要研究方向:自然语言处理、社交网络
    朱小飞(1979—),男,重庆人,教授,博士,CCF会员,主要研究方向:自然语言处理、信息检索 zxf@cqut.edu.cn
    高肇泽(1996—),男,山东枣庄人,硕士研究生,CCF会员,主要研究方向:自然语言处理、立场检测。
  • 基金资助:
    重庆市自然科学基金资助项目(CSTB2022NSCQ?MSX1672);重庆市教育委员会科学技术研究计划重大项目(KJZD?M202201102);重庆理工大学研究生教育高质量发展项目(gzlcx20233187)

Abstract:

Aiming at the problem that existing information diffusion prediction models are difficult to mine users’ dependency on cascades, a Prototype-aware Dual-channel Graph Convolutional neural Network (PDGCN) information diffusion prediction model was proposed. Firstly, HyperGraph Convolutional Network (HGCN) was used to learn user representation and cascade representation based on cascade hypergraph level, while Graph Convolutional Network (GCN) was used to learn user representation based on dynamic friendship forwarding graph. Secondly, for a given target cascade, the user representations that met the current cascade were found from the above two levels of user representations, and the two representations were fused together. Thirdly, the prototype of cascade representation was obtained through clustering algorithm. Finally, the most matching prototype for the current cascade was found, and this prototype was integrated into each user representation in the current cascade to calculate the diffusion probability of candidate users. Compared with Memory-enhanced Sequential HyperGraph ATtention network (MS-HGAT), PDGCN improved Hits@100 by 1.17% and MAP@100 by 5.02% on Twitter dataset, and improved Hits@100 by 3.88% and MAP@100 by 0.72% on Android dataset. Experimental results show that the proposed model outperforms the comparison model in information diffusion prediction task and has better prediction performance.

Key words: information diffusion prediction, prototype, hypergraph, dynamic graph, Graph Convolutional Network (GCN)

摘要:

针对现有的信息传播预测模型难以挖掘用户对级联的依赖关系的问题,提出一种原型感知双通道图卷积神经网络(PDGCN)的信息传播预测模型。首先,使用超图卷积网络(HGCN)学习基于级联超图级的用户表示和级联表示,同时使用图卷积网络(GCN)学习基于动态友谊转发图的用户表示;其次,对于给定的目标级联,分别从上述2个级别的用户表示中查找符合当前级联的用户表示,并融合这两种表示;再次,通过聚类算法得到级联表示的原型;最后,查找当前级联最匹配的原型,并使用该原型融入当前级联的每个用户表示,从而计算候选用户的传播概率。相较于记忆增强的顺序超图注意网络(MS-HGAT),在Twitter数据集上,PDGCN的Hits@100提升了1.17%,MAP@100提升了5.02%;在Android数据集上,PDGCN的Hits@100提升了3.88%,MAP@100提升了0.72%。实验结果表明,所提模型在信息传播预测任务上优于对比模型,具有更好的预测性能。

关键词: 信息传播预测, 原型, 超图, 动态图, 图卷积网络

CLC Number: