Attention-based network embedding with higher-order weights and node attributes  

作　　者：Xian Mo Binyuan Wan Rui Tang Junkai Ding Guangdi Liu 

机构地区：[1]School of Information Engineering,Ningxia University,Yinchuan,China [2]School of Cyber Science and Engineering,Sichuan University,Chengdu,China [3]Computer Science and Information Technology,University of Malaya,Kuala Lumpur,Malaysia [4]Academy of Medical Sciences,Zhengzhou University,Zhengzhou,China

出　　处：《CAAI Transactions on Intelligence Technology》2024年第2期440-451,共12页智能技术学报（英文）

基　　金：Key research and development projects of Ningxia,Grant/Award Number:2022BDE03007;Natural Science Foundation of Ningxia Province,Grant/Award Numbers:2023A0367,2021A0966,2022AAC05010,2022AAC03004,2021AAC03068。

摘　　要：Network embedding aspires to learn a low-dimensional vector of each node in networks,which can apply to diverse data mining tasks.In real-life,many networks include rich attributes and temporal information.However,most existing embedding approaches ignore either temporal information or network attributes.A self-attention based architecture using higher-order weights and node attributes for both static and temporal attributed network embedding is presented in this article.A random walk sampling algorithm based on higher-order weights and node attributes to capture network topological features is presented.For static attributed networks,the algorithm incorporates first-order to k-order weights,and node attribute similarities into one weighted graph to preserve topological features of networks.For temporal attribute networks,the algorithm incorporates previous snapshots of networks containing first-order to k-order weights,and nodes attribute similarities into one weighted graph.In addition,the algorithm utilises a damping factor to ensure that the more recent snapshots allocate a greater weight.Attribute features are then incorporated into topological features.Next,the authors adopt the most advanced architecture,Self-Attention Networks,to learn node representations.Experimental results on node classification of static attributed networks and link prediction of temporal attributed networks reveal that our proposed approach is competitive against diverse state-of-the-art baseline approaches.

关 键 词：data mining deep neural networks social network 

分 类 号：TN92[电子电信—通信与信息系统]