{"title":"Multi-channel set polynomial based label regularized graph neural networks against extreme data scarcity","authors":"Jingxiao Zhang , Shifei Ding , Jian Zhang , Lili Guo , Ling Ding","doi":"10.1016/j.patcog.2025.111754","DOIUrl":null,"url":null,"abstract":"<div><div>Graph Neural Networks (GNNs) are one of the commonly used methods for semi-supervised node classification. Their advantage lies in modeling the relational information in the data and propagating the feature information of labeled nodes to unlabeled nodes in the graph, thereby predicting their labels. However, current research results indicate that existing models perform poorly when labeled data are extremely limited. To address this problem, we introduce a label regularization method and propose a <strong>m</strong>ulti-channel <strong>s</strong>et <strong>p</strong>olynomial based <strong>l</strong>abel <strong>r</strong>egularized graph neural network against extreme data scarcity <strong>(MSP-LR)</strong>. It consists of two components: a basic learning module based on multi-channel set polynomials and a label regularization module. Specifically, we use the basic module to expand the model's receptive field and obtain pseudo-labels for all nodes. For labeled nodes, we replace the obtained pseudo-label information with their initial label information. In the label regularization module, we impose regularization constraints on unlabeled nodes based on the clustering assumption to improve the reliability of labels. Experimental results on two homogeneous graphs and four heterogeneous graphs with different labeling rates demonstrate the effectiveness of this model.</div></div>","PeriodicalId":49713,"journal":{"name":"Pattern Recognition","volume":"166 ","pages":"Article 111754"},"PeriodicalIF":7.5000,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pattern Recognition","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0031320325004145","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Graph Neural Networks (GNNs) are one of the commonly used methods for semi-supervised node classification. Their advantage lies in modeling the relational information in the data and propagating the feature information of labeled nodes to unlabeled nodes in the graph, thereby predicting their labels. However, current research results indicate that existing models perform poorly when labeled data are extremely limited. To address this problem, we introduce a label regularization method and propose a multi-channel set polynomial based label regularized graph neural network against extreme data scarcity (MSP-LR). It consists of two components: a basic learning module based on multi-channel set polynomials and a label regularization module. Specifically, we use the basic module to expand the model's receptive field and obtain pseudo-labels for all nodes. For labeled nodes, we replace the obtained pseudo-label information with their initial label information. In the label regularization module, we impose regularization constraints on unlabeled nodes based on the clustering assumption to improve the reliability of labels. Experimental results on two homogeneous graphs and four heterogeneous graphs with different labeling rates demonstrate the effectiveness of this model.
期刊介绍:
The field of Pattern Recognition is both mature and rapidly evolving, playing a crucial role in various related fields such as computer vision, image processing, text analysis, and neural networks. It closely intersects with machine learning and is being applied in emerging areas like biometrics, bioinformatics, multimedia data analysis, and data science. The journal Pattern Recognition, established half a century ago during the early days of computer science, has since grown significantly in scope and influence.