面向有向图的特征提取与表征学习研究  

Research on Feature Extraction and Representation Learning for Directed Graphs

作　　者：谭郁松[1] 张钰森[1] 蹇松雷 TAN Yusong;ZHANG Yusen+;JIAN Songlei(College of Computer Science and Technology,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学计算机学院,长沙410073

出　　处：《计算机工程与应用》2025年第3期234-241,共8页Computer Engineering and Applications

基　　金：国家自然科学基金(U19A2060,62002371);国防科技大学校科研基金(ZK21-17)。

摘　　要：图数据是一种用于描述不同实体之间关联关系的重要数据形式。有向图作为一种特殊形式,不仅能描述实体关联,还能明确关系的方向,提供了更精细和详实的描述。因此,有向图的特征提取和表征学习对于深入理解复杂系统具有至关重要的意义。然而,现有方法在有效提取有向图的方向信息方面仍然存在挑战,主要依赖于节点的局部信息进行特征提取,难以充分利用有向边蕴含的方向信息。为解决这一问题,提出了一种名为变分有向图自编码器(variational directed graph autoencoder,VDGAE)的无监督表示学习方法。VDGAE通过关联矩阵来建模节点与边之间的关联关系,通过计算节点与边之间的亲和力,来重构输入有向图,从而实现无监督表征学习。基于此,VDGAE能够同时为输入有向图学习节点与边的表征,充分捕获有向图的结构信息和方向信息并嵌入至节点与边的表征向量中,使得有向图能够被更准确地表征。实验结果表明,相较于11个基准方法,VDGAE在5个数据集上节点分类任务均优于基准方法,提升了11.96%的预测精度,充分验证了其有效性。Directed graphs,as a specific form of graph,not only describe entity relationships but also explicitly indicate the direction of these relationships,providing a more detailed and comprehensive description.Therefore,feature extraction and representation learning for directed graphs are crucial for understanding complex networks and have significant implications for practical applications.Despite the excellent performance of graph neural network(GNN)in extracting structural information from graphs,there are still challenges in effectively capturing directional information in directed graphs due to the limitations of their feature extraction patterns.This paper proposes an unsupervised representation learning method named variational directed graph autoencoder(VDGAE),based on the incidence matrix,which can simultaneously learn representations for nodes and edges to represent directed graphs effectively.Experimental results on five datasets demonstrate that VDGAE outperforms eleven baseline methods,achieving a 11.96%improvement in node classification,validating its effectiveness.

关 键 词：有向图 表征学习 关联矩阵 图神经网络 变分自编码器 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]