首页|面向节点分类任务的节点级自适应图卷积神经网络

面向节点分类任务的节点级自适应图卷积神经网络

扫码查看
图神经网络通过对图中节点的递归采样与聚合以学习节点嵌入,而现有方法中节点采样与聚合的模式较固定,对局部模式的多样性捕获存在不足,从而降低模型性能.因此,文中提出节点级自适应图卷积神经网络(Node-Level Adaptive Graph Convolutional Neural Network,NA-GCN).设计基于节点重要性的采样策略,自适应地确定各节点的邻域规模.同时,提出基于自注意力机制的聚合策略,自适应地融合给定邻域内的节点信息.在多个基准图数据集上的实验表明,NA-GCN在节点分类任务上具有较优性能.
Node-Level Adaptive Graph Convolutional Neural Network for Node Classification Tasks
Graph neural networks learn node embeddings by recursively sampling and aggregating information from nodes in a graph.However,the relatively fixed pattern of existing methods in node sampling and aggregation results in inadequate capture of local pattern diversity,thereby degrading the performance of the model.To solve this problem,a node-level adaptive graph convolutional neural network(NA-GCN)is proposed.A sampling strategy based on node importance is designed to adaptively determine the neighborhood size of each node.An aggregation strategy based on the self-attention mechanism is presented to adaptively fuse the node information within a given neighborhood.Experimental results on multiple benchmark graph datasets show the superiority of NA-GCN in node classification tasks.

Adaptive SamplingAdaptive AggregationNode ClassificationGraph Neural Networks(GNNs)Spectral Graph Theory

王鑫隆、胡睿、郭亚梁、杜航原、张槟淇、王文剑

展开 >

山西大学计算机与信息技术学院 太原 030006

山西警察学院网络安全保卫系 太原 030401

山西大学计算智能与中文信息处理教育部重点实验室 太原 030006

自适应采样 自适应聚合 节点分类 图神经网络(GNNs) 谱图理论

国家自然科学基金国家自然科学基金山西省重点研发计划山西省重点研发计划山西省基础研究计划

U21A2051362076154202202020101003202302010101007202303021221055

2024

模式识别与人工智能
中国自动化学会,国家智能计算机研究开发中心,中国科学院合肥智能机械研究所

模式识别与人工智能

CSTPCD北大核心
影响因子:0.954
ISSN:1003-6059
年,卷(期):2024.37(4)
  • 38