A novel graph oversampling framework for node classification in class-imbalanced graphs  

作　　者：Riting XIA Chunxu ZHANG Yan ZHANG Xueyan LIU Bo YANG 

机构地区：[1]Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education,Jilin University,Changchun 130012,China [2]College of Artificial Intelligence,Jilin University,Changchun 130012,China [3]College of Computer Science and Technology,Jilin University,Changchun 130012,China [4]College of Communication Engineering,Jilin University,Changchun 130012,China

出　　处：《Science China(Information Sciences)》2024年第6期210-225,共16页中国科学（信息科学）（英文版）

基　　金：supported by National Key R&D Program of China(Grant No.2021ZD0112500);National Natural Science Foundation of China(Grant Nos.U22A2098,62172185,62202200,62206105);Fundamental Research Funds for the Central Universities,JLU。

摘　　要：Graph neural network(GNN)is a promising method to analyze graphs.Most existing GNNs adopt the class-balanced assumption,which cannot deal with class-imbalanced graphs well.The oversampling technique is effective in alleviating class-imbalanced problems.However,most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs.They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling.In this paper,we propose a novel graph oversampling framework,termed distribution alignment-based oversampling for node classification in classimbalanced graphs(named Graph-DAO).Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs.Additionally,we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes.To our best knowledge,it is the first to use the sum-product network to solve the class-imbalanced problem in node classification.A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.

关 键 词：graph neural network class-imbalanced graphs sum-product network OVERSAMPLING node class-ification 

分 类 号：TP183[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]