Batch virtual adversarial training for graph convolutional networks

被引：4

作者：

Deng, Zhijie ^{[1
,2
]}

Dong, Yinpeng ^{[1
]}

Zhu, Jun ^{[1
]}

机构：

[1] Tsinghua Univ, Inst AI, BNRist Ctr, THU Bosch ML Ctr,Dept Comp Sci & Tech,THBI Lab, Beijing, Peoples R China

[2] Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai, Peoples R China

来源：

AI OPEN | 2023年 / 4卷

关键词：

Virtual adversarial training; Graph convolutional networks; Semi-supervised node classification;

D O I：

10.1016/j.aiopen.2023.08.007

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the issue that GCNs do not ensure the smoothness of the model's output distribution against local perturbations around the input node features. We propose two algorithms, samplingbased BVAT and optimization -based BVAT, which promote the output smoothness of GCN classifiers based on the generated virtual adversarial perturbations for either a subset of independent nodes or all nodes via an elaborate optimization process. Extensive experiments on three citation network datasets Cora , Citeseer and Pubmed and a knowledge graph dataset Nell validate the efficacy of the proposed method in semi -supervised node classification tasks.

引用

页码：73 / 79

页数：7