面向图神经网络的节点重要性排序研究进展
Advances in Node Importance Ranking Based on Graph Neural Networks
摘要
Abstract
Node importance ranking is a critical task in graph analysis,as it plays a crucial role in identifying and prioritizing important nodes within a graph.Graph neural networks(GNNs)serve as an effective framework that leverages deep learning to directly comprehend the structural data of graphs,enabling comprehensive understanding of the internal patterns and deeper semantic features associated with nodes and edges.In the context of node importance ranking,GNNs can effectively harness graph structure information and node features to assess the significance of individual nodes.Compared with tradi-tional node ranking methods,GNNs are better equipped to handle the diverse and intricate nature of graph structural data,capturing complex associations and semantic information between nodes while autonomously learning representations for node features.This reduces reliance on manual feature engineering,thereby enhancing accuracy in node importance ranking tasks.Consequently,approaches based on graph neural networks have emerged as the predominant direction for research into node importance.On this basis,this paper provides a classification of recent advancements in node ranking methods utilizing graph neural networks.This paper begins by revisiting core concepts related to node ranking,graph neural net-works,and classical metrics for assessing node importance.It then summarizes recent developments in methods for evalu-ating node importance using graph neural networks.These techniques are categorized into four groups based on fun-damental graph neural networks and their variants:basic GNNs,graph convolutional neural networks(GCNs),graph attention networks(GATs),and graph autoencoders(GAEs).Additionally,this paper analyzes the performance of these methods across various application domains,such as social networks,traffic networks,and knowledge graphs.Finally,it offers a comprehensive overview of existing research by analyzing time complexity along with advantages,limitations,and performance characteristics of current methodologies.Furthermore,it discusses future research directions based on identified shortcomings.关键词
节点重要性/节点排序/图神经网络/表示学习Key words
node importance/node ranking/graph neural network/representation learning分类
计算机与自动化引用本文复制引用
曹璐,丁苍峰,马乐荣,延照耀,游浩,洪安琪..面向图神经网络的节点重要性排序研究进展[J].计算机科学与探索,2025,19(4):877-900,24.基金项目
国家自然科学基金(62262067) （62262067）
陕西省人才项目(YAU202213065,CXY202107) （YAU202213065,CXY202107）
延安大学"十四五"重大科研项目(2021ZCQ012) （2021ZCQ012）
延安大学基金项目(YCX2024049,YDBK2018-35,D2022034) （YCX2024049,YDBK2018-35,D2022034）
教学改革研究项目(YDJG23-27) （YDJG23-27）
大学生创新创业训练项目(202210719034,S202310719075).This work was supported by the National Natural Science Foundation of China(62262067),the Talent Project of Shaanxi Province(YAU202213065,CXY202107),the Major Scientific Research Project of Yan'an University During the 14th Five-Year Plan(2021ZCQ012),the Fund Project of Yan'an University(YCX2024049,YDBK2018-35,D2022034),the Teaching Reform Research Project(YDJG23-27),and the College Students'Innovation and Entrepreneurship Training Projects(202210719034,S202310719075). （202210719034,S202310719075）
