Few-shot node classification via local adaptive discriminant structure learning  

作　　者：Zhe XUE Junping DU Xin XU Xiangbin LIU Junfu WANG Feifei KOU 

机构地区：[1]Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia,School of Computer Science,Beijing University of Posts and Telecommunications,Beijing 100876,China

出　　处：《Frontiers of Computer Science》2023年第2期135-143,共9页中国计算机科学前沿（英文版）

基　　金：supported by the National Key R&D Program of China(2018YFB1402600);the National Natural Science Foundation of China(Grant Nos.61802028,62192784,61877006,and 62002027)。

摘　　要：Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes.Most of the existing node classification methods cannot be used for few-shot node classification.To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples,in this paper,we propose a local adaptive discriminant structure learning(LADSL)method for few-shot node classification.LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlargingginter-classdifferences.Extensiveexperiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.

关 键 词：few-shot learning node classification graph neural network adaptive structure learning attention strategy 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]