基于多维云概念嵌入的变分图自编码器研究

代劲; 张奇瑞; 王国胤; 彭艳辉; 涂盛霞

doi:10.12263/DZXB.20220354

您当前的位置：

首页 >

文章列表页 >

基于多维云概念嵌入的变分图自编码器研究

学术论文 | 更新时间：2025-12-11

- 基于多维云概念嵌入的变分图自编码器研究
- Research on Variational Graph Auto-Encoder Based on Multidimensional Cloud Concept Embedding
- 电子学报 2023年51卷第12期页码：3507-3519
- 作者机构：
  
  1.重庆邮电大学计算智能重庆市重点实验室,重庆 400065
  2.重庆邮电大学软件工程学院,重庆 400065
  3.重庆邮电大学旅游多源数据感知与决策技术文化和旅游部重点实验室,重庆 400065
  4.华为技术有限公司,广东深圳 518129
- 作者简介：
  
  [ "代劲男，1978年出生于贵州遵义.博士，重庆邮电大学教授，硕士生导师．主要研究方向为粒计算、认知计算、智能信息处理．E-mail: daijin@cqupt.edu.cn" ]
  [ "张奇瑞男，1997年出生于四川德阳，硕士生．主要研究方向为智能信息处理、数据挖掘.E-mail: S201201035@stu.cqupt.edu.cn" ]
  [ "王国胤男，1970年出生于重庆市，博士，教授，博士生导师．教育部“长江学者”特聘教授（2015-2019）、中组部“万人计划”科技创新领军人才（2014）、人社部“新世纪百千万人才工程”国家级人选、国务院特殊津贴专家、中科院“百人计划”专家、教育部“新世纪优秀人才”．主要研究方向为粗糙集、粒计算、数据挖掘、认知计算、大数据、人工智能等．E-mail: wanggy@cqupt.edu.cn" ]
  [ "彭艳辉女，1998年出生于重庆丰都，硕士生．主要研究方向为智能信息处理、数据挖掘．E-mail: S211201018@stu.cqupt.edu.cn" ]
  [ "涂盛霞女，1993年出生于湖北潜江，硕士，华为大数据高级工程师，主要研究方向为大数据引擎及性能优化．E-mail: tushengxia@huawei.com" ]
- 基金信息：
  
  国家自然科学基金(61936001;61772096);重庆市自然科学基金(cstc2021jcyj-msxmX0849)
- DOI：10.12263/DZXB.20220354
  中图分类号： TP18
- 收稿：2022-04-06，
  
  修回：2023-01-30，
  
  纸质出版：2023-12-25
- 稿件说明：
移动端阅览
代劲,张奇瑞,王国胤等.基于多维云概念嵌入的变分图自编码器研究[J].电子学报,2023,51(12):3507-3519.

DAI Jin,ZHANG Qi-rui,WANG Guo-ying,et al.Research on Variational Graph Auto-Encoder Based on Multidimensional Cloud Concept Embedding[J].ACTA ELECTRONICA SINICA,2023,51(12):3507-3519.
代劲,张奇瑞,王国胤等.基于多维云概念嵌入的变分图自编码器研究[J].电子学报,2023,51(12):3507-3519. DOI： 10.12263/DZXB.20220354.

DAI Jin,ZHANG Qi-rui,WANG Guo-ying,et al.Research on Variational Graph Auto-Encoder Based on Multidimensional Cloud Concept Embedding[J].ACTA ELECTRONICA SINICA,2023,51(12):3507-3519. DOI： 10.12263/DZXB.20220354.

摘要

变分图自编码器是图嵌入研究中重要的深度学习模型，但存在着先验正态分布缺陷、训练过程中容易出现后验塌陷等问题．本文从建立云概念空间与隐空间的映射关系入手，引入云模型数字特征对网络中的节点进行不确定性概念表示，设计了一种基于多维云模型的变分图自编码器（Variational Graph Autoencoder based on Multidimensional Cloud Model，MCM-VGAE）．该模型实现了隐空间的多维云概念嵌入及相应的漂移性损失度量，将先验分布扩展为泛正态分布，利用多维正向云发生器及云包络带修正采样算法实现了重参数化过程，有效缓解了后验塌陷现象．在应用效果上，模型在多类型数据集上的链路预测、节点聚类、图嵌入可视化实验表现均优于基准模型，进一步说明了方法的普适有效性．

Abstract

Variational graph autoencoder (VGAE) is a significant deep learning model in graph embedding

but there are problems such as the normal prior distribution defect and the posterior collapse during training. Focusing on establishing the mapping relationship between cloud concept space and hidden space

the uncertain concepts of nodes in VGAE network are represented by the digital features of cloud model

and an optimized VGAE model based on multidimensional cloud model (MCM-VGAE) is reconstructed. The model implements a multidimensional cloud concept embedding in the latent space and the corresponding drift loss measure

extends the prior distribution to a generic normal distribution

and uses a multidimensional forward cloud generator and a cloud envelope with modified sampling algorithm to realize the reparameterization process and effectively mitigate the posterior collapse phenomenon. In terms of application

the model outperforms the benchmark model for link prediction

node clustering

and graph embedding visualization experiments on multi-type datasets

further illustrating the universal effectiveness of the method.

关键词

Keywords

references

李德毅 , 刘常昱 , 杜鹢 , 等 . 不确定性人工智能 [J ] . 软件学报 , 2004 , 15 ( 11 ): 1583 - 1594 .

LI D Y , LIU C Y , DU Y , et al . Artificial intelligence with uncertainty [J ] . Journal of Software , 2004 , 15 ( 11 ): 1583 - 1594 . (in Chinese)

祁志卫 , 王笳辉 , 岳昆 , 等 . 图嵌入方法与应用: 研究综述 [J ] . 电子学报 , 2020 , 48 ( 4 ): 808 - 818 .

QI Z W , WANG J H , YUE K , et al . Methods and applications of graph embedding: A survey [J ] . Acta Electronica Sinica , 2020 , 48 ( 4 ): 808 - 818 . (in Chinese)

吴博 , 梁循 , 张树森 , 等 . 图神经网络前沿进展与应用 [J ] . 计算机学报 , 2022 , 45 ( 1 ): 35 - 68 .

WU B , LIANG X , ZHANG S S , et al . Advances and applications in graph neural network [J ] . Chinese Journal of Computers , 2022 , 45 ( 1 ): 35 - 68 . (in Chinese)

KIPF T N , WELLING M . Variational graph auto-encoders [EB/OL ] .( 2016-11-21 )[ 2022-03-06 ] . https://arxiv.org/abs/1611.07308 https://arxiv.org/abs/1611.07308 .

PAN S R , HU R Q , LONG G D , et al . Adversarially regularized graph autoencoder for graph embedding [C ] // Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence . Stockholm : AAAI , 2018 : 2609 - 2615 .

HASANZADEH A , HAJIRAMEZANALI E , DUFFIELD N , et al . Semi-implicit graph variational auto-encoders [EB/OL ] . ( 2019-09-07 )[ 2022-03-06 ] . https://arxiv.org/abs/1908.07078 https://arxiv.org/abs/1908.07078 .

AHN S J , KIM M . Variational graph normalized AutoEncoders [C ] // Proceedings of the 30th ACM International Conference on Information & Knowledge Management . New York : ACM , 2021 : 2827 - 2831 .

SALHA G , HENNEQUIN R , VAZIRGIANNIS M . Simple and effective graph autoencoders with one-hop linear models [M ] // Machine Learning and Knowledge Discovery in Databases . Cham : Springer International Publishing , 2021 : 319 - 334 .

李德毅 , 刘常昱 . 论正态云模型的普适性 [J ] . 中国工程科学 , 2004 , 6 ( 8 ): 28 - 34 .

LI D Y , LIU C Y . Study on the universality of the normal cloud model [J ] . Strategic Study of CAE , 2004 , 6 ( 8 ): 28 - 34 . (in Chinese)

ZHU Q L , BI W , LIU X J , et al . A batch normalized inference network keeps the KL vanishing away [C ] // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics . Stroudsburg : Association for Computational Linguistics , 2020 : 2636 - 2649 .

杨洁 , 王国胤 , 刘群 , 等 . 正态云模型研究回顾与展望 [J ] . 计算机学报 , 2018 , 41 ( 3 ): 724 - 744 .

YANG J , WANG G Y , LIU Q , et al . Retrospect and prospect of research of normal cloud model [J ] . Chinese Journal of Computers , 2018 , 41 ( 3 ): 724 - 744 . (in Chinese)

TIAN F , GAO B , CUI Q , et al . Learning deep representations for graph clustering [C ] // Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence . Quebec : AAAI , 2014 : 1293 - 1299 .

Davidson T R , Falorsi L , De Cao N , et al . Hyperspherical variational auto-encoders [EB/OL ] . ( 2018-04-03 )[ 2022-03-06 ] . https://arxiv.org/abs/1804.00891 https://arxiv.org/abs/1804.00891 .

过江 , 张为星 , 赵岩 . 岩爆预测的多维云模型综合评判方法 [J ] . 岩石力学与工程学报 , 2018 , 37 ( 5 ): 1199 - 1206 .

GUO J , ZHANG W X , ZHAO Y . A multidimensional cloud model for rockburst prediction [J ] . Chinese Journal of Rock Mechanics and Engineering , 2018 , 37 ( 5 ): 1199 - 1206 . (in Chinese)

LIU L , ZHOU T Y , LONG G D , et al . Prototype propagation networks (PPN) for weakly-supervised few-shot learning on category graph [C ] // Proceedings of the 28th International Joint Conference on Artificial Intelligence . New York : ACM , 2019 : 3015 - 3022 .

代劲 , 胡彪 , 王国胤 , 等 . 分布轮廓与局部特征融合的云模型不确定性相似度量 [J ] . 电子与信息学报 , 2022 , 44 ( 4 ): 1429 - 1439 .

DAI J , HU B , WANG G Y , et al . The uncertainty similarity measure of cloud model based on the fusion of distribution contour and local feature [J ] . Journal of Electronics & Information Technology , 2022 , 44 ( 4 ): 1429 - 1439 . (in Chinese)

陈昊 , 龙文佳 . 高斯云模型的雾化特性 [J ] . 湖北大学学报(自然科学版) , 2015 , 37 ( 6 ): 560 - 564 .

CHEN H , LONG W J . The atomization characteristics in Gauss cloud model [J ] . Journal of Hubei University (Natural Science Edition) , 2015 , 37 ( 6 ): 560 - 564 . (in Chinese)

CHIANG W L , LIU X Q , SI S , et al . Cluster-GCN: An efficient algorithm for training deep and large graph convolutional networks [C ] // Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . New York : ACM , 2019 : 257 - 266 .

YANG Z , COHEN W W , SALAKHUTDINOV R . Revisiting semi-supervised learning with graph embeddings [EB/OL ] . ( 2016-03-29 )[ 2022-03-06 ] . https://arxiv.org/abs/1603.08861 https://arxiv.org/abs/1603.08861 .

SHCHUR O , MUMME M , BOJCHEVSKI A , et al . Pitfalls of graph neural network evaluation [EB/OL ] . ( 2018-11-14 )[ 2022-03-06 ] . https://arxiv.org/abs/1811.05868 https://arxiv.org/abs/1811.05868 .

FEY M , LENSSEN J E . Fast graph representation learning with PyTorch geometric [EB/OL ] . ( 2019-03-06 )[ 2022-03-06 ] . https://arxiv.org/abs/1903.02428 https://arxiv.org/abs/1903.02428 .

TU C C , ZENG X K , WANG H , et al . A unified framework for community detection and network representation learning [J ] . IEEE Transactions on Knowledge and Data Engineering , 2019 , 31 ( 6 ): 1051 - 1065 .

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

基于深度卷积神经网络的多节点间链路预测方法

基于Attention深度随机森林的社区演化事件预测

面向高光谱遥感影像分类的监督多流形鉴别嵌入方法

动态网络表示学习研究进展