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

作　　者：代劲[1,2] 张奇瑞 王国胤[1,3] 彭艳辉 涂盛霞 DAI Jin;ZHANG Qi-rui;WANG Guo-ying;PENG Yan-hui;TU Sheng-xia(Chongqing Key Laboratory of Computation Intelligence,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;School of Software Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;Key Laboratory of Tourism Multisource Data Perception and Decision,Ministry of Culture and Tourism,Chongqing University of Posts and Telecommunication,Chongqing 400065,China;Huawei Technologies Co.,Ltd.,Shenzhen,Guangdong 518129,China)

机构地区：[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

出　　处：《电子学报》2023年第12期3507-3519,共13页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61936001,No.61772096);重庆市自然科学基金(No.cstc2021jcyj-msxmX0849)。

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.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：变分图自编码器 图嵌入 多维云模型 概念嵌入 链路预测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]