首页|基于霍克斯过程的动态异质网络表征学习方法

基于霍克斯过程的动态异质网络表征学习方法

扫码查看
现有的异质网络表征学习方法主要关注静态网络,忽略了时间属性对节点表示的重要影响.然而,真实的异质信息网络极具动态性,节点和边的微小变化都可能影响整个结构和语义.鉴于此,提出了基于霍克斯过程的动态异质网络表征学习方法.首先,利用关系旋转编码方式和注意力机制,学习相邻节点的注意力系数,获得节点的向量表示.其次,学习不同元路径的最优加权组合以更好捕获网络的结构和语义信息.最后,基于时间衰减效应,通过邻域形成序列将时间特征引入节点表示中,得到节点的最终嵌入表示.在多种基准数据集上的实验结果表明,所提方法在性能上显著优于对比模型.在节点分类任务中,Macro-F1平均提高了0.15%~3.45%,在节点聚类任务中,归一化互信息(normalized mutual information,NMI)值提高了1.08%~3.57%.
Dynamic heterogeneous network representation learning method based on Hawkes process
Existing methods for heterogeneous network representation learning mainly focus on static networks,over-looking the significant impact of temporal attributes on node representations. However,real heterogeneous informa-tion networks are very dynamic,and even minor changes in nodes and edges can affect the entire structure and seman-tics. In this context,a dynamic heterogeneous network representation learning method based on Hawkes process was proposed. Firstly,the vector representation of nodes was obtained by utilizing the relational rotation encoding method and attention mechanism,where the attention coefficients of adjacent nodes were learned. Secondly,the optimal weighted combination of different meta-paths was learned to better captures the structural and semantic information of the network. Finally,leveraging the time decay effect,time features were introduced into node representations through the formation of neighborhood sequences,resulting in the ultimate embedding representation of nodes. Ex-perimental results on various benchmark datasets indicate that the proposed method significantly outperforms baseline methods. In node classification tasks,Macro-F1 average is increased by 0.15% to 3.45%,and NMI value in node clus-tering tasks is improved by 1.08% to 3.57%.

network representation learningdynamic heterogeneous information networkattention mechanismmeta-pathHawkes process

陈蕾、邓琨、刘星妍

展开 >

嘉兴大学信息科学与工程学院,浙江嘉兴 314001

浙江师范大学计算机科学与技术学院(人工智能学院),浙江金华 321004

嘉兴大学浙江省医学电子与数字健康重点实验室,浙江嘉兴 314001

网络表征学习 动态异质信息网络 注意力机制 元路径 霍克斯过程

2024

电信科学
中国通信学会 人民邮电出版社

电信科学

CSTPCD北大核心
影响因子:0.902
ISSN:1000-0801
年,卷(期):2024.40(8)