基于局部优化的图表示学习增强  

Graph Representation Learning Enhancement Based on Local Optimization

作　　者：唐正正 汪洋[1,2] 洪学海 班艳[1] 姚铁锤 乔子越 Tang Zhengzheng;Wang Yang;Hong Xuehai;Ban Yan;Yao Tiechui;Qiao Ziyue(Center of Information Development Strategy and Evaluation,Computer Network Information Center,Chinese Academy of Sciences,Beijing 100190;School of Computer Science and Technology,University of Chinese Academy of Sciences,Beijing 100049;Strategy Research Center of Information Technology,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190)

机构地区：[1]中国科学院计算机网络信息中心信息化发展战略与评估中心,北京100190 [2]中国科学院大学计算机科学与技术学院,北京100049 [3]中国科学院计算技术研究所信息技术战略研究中心,北京100190

出　　处：《计算机研究与发展》2023年第9期2080-2095,共16页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(92046017);中国科学院信息化工程项目(XXH13504-03)。

摘　　要：随着图表示学习在多个领域的成功应用,针对不同图数据和问题而设计的图表示学习方法爆发式增长.然而,图噪声的存在限制了图表示学习的能力.为有效降低图网络中的噪声比例,首先分析了图节点局部邻接的分布特性,并理论证明在局部邻接拓扑构建时,探索高阶邻近信息能够优化增强图表示学习的性能.其次,提出“2步骤”局部子图优化策略(local subgraph optimization strategy,LSOS).该策略首先根据原始图拓扑结构信息构造出具有多阶信息的局部邻接相似矩阵.然后基于相似矩阵和图节点局部信息,对图节点进行局部子图的结构优化.通过局部邻接的合理重构来降低网络中的噪声比例,进而达到图表示学习能力的增强.在节点分类、链接预测和社区发现3类任务的实验中,结果表明局部子图优化策略能够提升8个基线算法的性能.其中,在3个航空网络的节点分类任务中,提升效果最高分别达到23.11%,41.58%,24.16%.With the successful application of graph representation learning in multiple fields,graph representation learning methods designed for different graph data and problems have exploded.However,the existence of graph noise limits the ability of graph representation learning.In order to effectively reduce the proportion of noise in the graph network,we first analyze the distribution characteristics of the local adjacency of the graph nodes,and theoretically prove that in the construction of the local adjacency topology,exploring high-order neighbor information can optimize the performance of the enhanced graph representation learning.Second,we propose“2-Steps”local subgraph optimization strategy(LOSO).This strategy first constructs a local adjacency similarity matrix with multi-order information based on the original graph topology information.Then,based on the similarity matrix and the local information of the graph nodes,the graph nodes are locally subgraph structure optimization.The proportion of noise in the network through the reasonable reconstruction of local adjacencies is reduced,and then the enhancement of graph representation learning ability is achieved.In the experiments of node classification,link prediction and community discovery tasks,the results indicate the local subgraph optimization strategy in this paper can boost the performance of 8 baseline algorithms.Among them,in the node classification tasks of the three aviation networks,the highest improvement effect reaches 23.11%,41.58%,and 24.16%,respectively.

关 键 词：图表示学习 图噪声 节点分类 链接预测 社区发现 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]