用于半监督分类的二阶近似谱图卷积模型  

Two-order Approximate Spectral Convolutional Model for Semi-Supervised Classification

作　　者：公沛良 艾丽华[1,2] GONG Pei-Liang;AI Li-Hua(School of Computer and Information Technology,BeijingJiaotong University,Beijing 100044;Beijing Key Laboratory of Traffic Data Analysis and Mining,Beijing 100044)

机构地区：[1]北京交通大学计算机与信息技术学院,北京100044 [2]交通数据分析与挖掘北京市重点实验室,北京100044

出　　处：《自动化学报》2021年第5期1067-1076,共10页Acta Automatica Sinica

基　　金：国家自然科学基金(61472029,51827813,61473031)资助。

摘　　要：近年来,基于局部一阶近似的谱图卷积方法在半监督节点分类任务上取得了明显优势,但是在每次更新节点特征表示时,只利用了一阶邻居节点信息而忽视了非直接邻居节点信息.为此,本文结合切比雪夫截断展开式及标准化的拉普拉斯矩阵,通过推导及简化二阶近似谱图卷积模块,提出了一种融合丰富局部结构信息的改进图卷积模型,进一步提高了节点分类性能.大量的实验结果表明,本文提出的方法在不同数据集上的表现均优于现有的流行方法,验证了模型的有效性.In recent years,the spectral convolution method based on local first-order approximation has achieved significant advantages in semi-supervised node classification tasks.However,when updating the node feature representation at each stage,only the first-order neighbor node information is used,while the indirect neighbor node information is ignored.To this end,this paper combines Chebyshev′s truncated expansion and symmetric normalized Laplacian matrix,and by deducing and simplifying the two-order approximate spectral convolution module,an improved graph convolution model is proposed which fuses rich local structure information.A large number of experimental results show that the method proposed in this paper is superior to the existing popular methods on different datasets,which verifies the effectiveness of the model.

关 键 词：图理论 谱图卷积 半监督学习 节点分类 关系数据 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] O157.5[自动化与计算机技术—控制科学与工程]