注意力感知的边-节点交换图神经网络模型

王瑞琴; 黄熠旻; 纪其顺; 万超艺; 周志峰

doi:10.11959/j.issn.1000-0801.2024017

您当前的位置：

首页 >

文章列表页 >

注意力感知的边-节点交换图神经网络模型

研究与开发 | 更新时间：2024-06-05

- 注意力感知的边-节点交换图神经网络模型
- Attention aware edge-node exchange graph neural network
- 电信科学 2024年40卷第1期页码：106-114
- 作者机构：
  
  1. 湖州师范学院信息工程学院，浙江湖州 313000
  2. 温州大学图书馆，浙江温州 325035
- 作者简介：
  
  [ "王瑞琴（1979- ），女，博士，湖州师范学院信息工程学院教授，主要研究方向为自然语言处理、社交网络分析、个性化推荐" ]
  [ "黄熠旻（1998- ），男，湖州师范学院信息工程学院硕士生，主要研究方向为机器学习、数据挖掘、个性化推荐" ]
  [ "纪其顺（1996- ），男，湖州师范学院信息工程学院硕士生，主要研究方向为自然语言处理、数据挖掘" ]
  [ "万超艺（1997- ），女，湖州师范学院信息工程学院硕士生，主要研究方向为自然语言处理、数据挖掘" ]
  [ "周志峰（1978- ），男，博士，温州大学图书馆副研究员，主要研究方向为信息检索、数据挖掘" ]
- 基金信息：
  
  国家自然科学基金资助项目;The National Natural Science Foundation of China(62277016)
- DOI：10.11959/j.issn.1000-0801.2024017
  中图分类号： TP393
- 网络出版日期：2024-01，
  
  纸质出版日期：2024-01-20
- 稿件说明：
移动端阅览
王瑞琴, 黄熠旻, 纪其顺, 等. 注意力感知的边-节点交换图神经网络模型[J]. 电信科学, 2024,40(1):106-114.

Ruiqin WANG, Yimin HUANG, Qishun JI, et al. Attention aware edge-node exchange graph neural network[J]. Telecommunications science, 2024, 40(1): 106-114.
王瑞琴, 黄熠旻, 纪其顺, 等. 注意力感知的边-节点交换图神经网络模型[J]. 电信科学, 2024,40(1):106-114. DOI： 10.11959/j.issn.1000-0801.2024017.

Ruiqin WANG, Yimin HUANG, Qishun JI, et al. Attention aware edge-node exchange graph neural network[J]. Telecommunications science, 2024, 40(1): 106-114. DOI： 10.11959/j.issn.1000-0801.2024017.

摘要

提出了一种注意力感知的边-节点交换图神经网络（attention aware edge-node exchange graph neural network，AENN）模型，在图结构化数据表示框架下，使用边-节点切换卷积的图神经网络算法进行图编码，用于半监督分类和回归分析。AENN 是一种通用的图编码框架，用于将图节点和边嵌入一个统一的潜在特征空间。具体地，基于原始无向图，不断切换边与节点的卷积，并在卷积过程中通过注意力机制分配不同邻居的权重，从而实现特征传播。在 3 个数据集上的实验研究表明，所提方法较已有方法在半监督分类和回归分析中具有明显的性能提升。

Abstract

An attention aware edge-node exchange graph neural network (AENN) model was proposed

which used edge-node switched convolutional graph neural network method for graph encoding in a graph structured data representation framework for semi supervised classification and regression analysis.AENN is an universal graph encoding framework for embedding graph nodes and edges into a unified latent feature space.Specifically

based on the original undirected graph

the convolution between edges and nodes was continuously switched

and during the convolution process

attention mechanisms were used to assign weights to different neighbors

thereby achieving feature propagation.Experimental studies on three datasets show that the proposed method has significant performance improvements in semi-supervised classification and regression analysis compared to existing methods.

关键词

Keywords

references

CHEN C , ZHANG M , ZHANG Y F , et al . Efficient neural matrix factorization without sampling for recommendation [J ] . ACM Transactions on Information Systems , 2020 , 38 ( 2 ): 1 - 28 .

CHEN L , WU L , HONG R C , et al . Revisiting graph based collaborative filtering:a linear residual graph convolutional network approach [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 1 ): 27 - 34 .

CHEN M , WEI Z W , HUANG Z F , et al . Simple and deep graph convolutional networks [J ] . arXiv preprint , 2020 ,arXiv:2007.02133.

XIA X , YIN H , YU J , et al . Self-supervised hypergraph convolutional networks for session-based recommendation [C ] // Proceedings of the AAAI conference on artificial intelligence . 2021 , 35 ( 5 ): 4503 - 4511 .

WU J C , WANG X , FENG F L , et al . Self-supervised graph learning for recommendation [C ] // Proceedings of the Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval . New York:ACM Press , 2021 : 726 - 735 .

YU W H , QIN Z . Graph convolutional network for recommendation with low-pass collaborative filters [C ] // Proceedings of the Proceedings of the 37th International Conference on Machine Learning . New York:ACM Press , 2020 : 10936 - 10945 .

YU W H , QIN Z . Sampler design for implicit feedback data by noisy-label robust learning [C ] // Proceedings of the Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval . New York:ACM Press , 2020 : 861 - 870 .

SUN J N , GUO W , ZHANG D C , et al . A framework for recommending accurate and diverse items using Bayesian graph convolutional neural networks [C ] // Proceedings of the Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery ＆ Data Mining . New York:ACM Press , 2020 : 2030 - 2039 .

JI S Y , FENG Y F , JI R R , et al . Dual channel hypergraph collaborative filtering [C ] // Proceedings of the Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery ＆ Data Mining . New York:ACM Press , 2020 : 2020 - 2029 .

WANG M H , LIN Y J , LIN G L , et al . M2GRL:a multi-task multi-view graph representation learning framework for web-scale recommender systems [C ] // Proceedings of the Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery ＆ Data Mining . New York:ACM Press , 2020 : 2349 - 2358 .

ZHANG H , LIU Q , LIU Z . Simplification of graph convolutional networks:a matrix factorization-based perspective [J ] . arXiv preprint , 2020 ,arXiv:2007.09036.

MAO K , ZHU J , XIAO X , et al . UltraGCN:ultra simplification of graph convolutional networks for recommendation [J ] . arXiv preprint , 2021 ,arXiv:2110.15114.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

GMTBLC：基于深度学习的双模态网络流量分类

基于改进长短期记忆网络的新能源场站网络安全评估方法研究

基于霍克斯过程的动态异质网络表征学习方法

基于图神经网络的鲁棒加密流量识别

信号增强网络驱动的调制识别