山西大学学报（自然科学版）2025，Vol.48Issue(1)：29-42,14.DOI:10.13451/j.sxu.ns.2024134
基于结构学习和自监督图注意力的网络表示学习
Network Representation Learning Based on Structural Learning and Self-supervised Graph Attention
摘要
Abstract
Network representation learning is the foundation of network analysis tasks,that holds significant importance in mining and analyzing the real network data.Recently,Graph Attention Networks(GAT)and their variants have shown exceptional perfor-mance.This is particularly evident in the field of network representation learning.However,attention-based methods have the fol-lowing limitations:(1)Only first-order neighbor information of nodes is considered,ignoring higher-order neighbors.(2)The model lacks interpretability.(3)The issue of noisy edges in the graph is not considered.To tackle these issues,this paper proposes a Struc-tural Learning and Self-supervised Graph Attention Network Embedding Model(SL-SGAT),which integrates node features and structural information,reduces noise edge interference,and enhances model interpretability.SL-SGAT mainly consists of three parts:graph structure learning,self-supervised attention mechanism,and feature aggregation.Graph structure learning constructs a global graph structure network.The self-supervised attention mechanism sets up a self-supervised relation prediction task,with noise edge loss added.Feature aggregation utilizes attention coefficients for weighted aggregation to obtain the final node embedding represen-tation.The model proposed in this paper was tested on the Cora,Citeseer,and Pubmed datasets for node classification tasks,achiev-ing accuracies of 84.4％,74.4％,and 81.5％,respectively.Compared to the high-performing GAT and its subsequent variants,our model shows improvements of 1.4％,2.9％,and 3.2％,respectively.In the node clustering experiments,the clustering accuracy im-proved by 3.3％,3.4％,and 1.2％.These results demonstrate that our proposed algorithm can achieve a better representation of node embedding.关键词
网络表示学习/图注意力网络/自监督学习/图结构学习/节点分类Key words
network representation learning/graph attention network/self-supervised learning/graph structure learning/node classi-fication分类
信息技术与安全科学引用本文复制引用
王静红,郑瑞策,米据生,李昊康..基于结构学习和自监督图注意力的网络表示学习[J].山西大学学报（自然科学版）,2025,48(1):29-42,14.基金项目
河北省科学基金资助项目(F20242050280) （F20242050280）
河北省高等学校科学技术研究项目(ZD2022139) （ZD2022139）
