Research on Variational Graph Auto-Encoder Based on Multidimensional Cloud Concept Embedding

被引：0

作者：

Dai J. ^{[1
,2
]}

Zhang Q.-R. ^{[2
]}

Wang G.-Y. ^{[1
,3
]}

Peng Y.-H. ^{[2
]}

Tu S.-X. ^{[4
]}

机构：

[1] Chongqing Key Laboratory of Computation Intelligence, Chongqing University of Posts and Telecommunications, Chongqing

[2] School of Software Engineering, Chongqing University of Posts and Telecommunications, Chongqing

[3] Key Laboratory of Tourism Multisource Data Perception and Decision, Ministry of Culture and Tourism, Chongqing University of Posts and Telecommunication, Chongqing

[4] Huawei Technologies Co.，Ltd., Guangdong, Shenzhen

来源：

Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2023年 / 51卷 / 12期

基金：

中国国家自然科学基金;

关键词：

concept embedding; graph embedding; link prediction; multidimensional cloud model; variational graph autoencoder;

D O I：

10.12263/DZXB.20220354

中图分类号：

学科分类号：

摘要：

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 repa-rameterization 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. © 2023 Chinese Institute of Electronics. All rights reserved.

引用

页码：3507 / 3519

页数：12

共 22 条

[1] LI D Y, LIU C Y, DU Y, Et al., Artificial intelligence with uncertainty, Journal of Software, 15, 11, pp. 1583-1594, (2004)
[2] QI Z W, WANG J H, YUE K, Et al., Methods and applications of graph embedding: A survey, Acta Electronica Sinica, 48, 4, pp. 808-818, (2020)
[3] WU B, LIANG X, ZHANG S S, Et al., Advances and applications in graph neural network, Chinese Journal of Computers, 45, 1, pp. 35-68, (2022)
[4] KIPF T N, WELLING M., Variational graph auto-encoders
[5] PAN S R, HU R Q, LONG G D, Et al., Adversarially regularized graph autoencoder for graph embedding, Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pp. 2609-2615, (2018)
[6] HASANZADEH A, HAJIRAMEZANALI E, DUFFIELD N, Et al., Semi-implicit graph variational auto-encoders
[7] AHN S J, KIM M., Variational graph normalized AutoEncoders, Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp. 2827-2831, (2021)
[8] SALHA G, HENNEQUIN R, VAZIRGIANNIS M., Simple and effective graph autoencoders with one-hop linear models, Machine Learning and Knowledge Discovery in Databases, pp. 319-334, (2021)
[9] LI D Y, LIU C Y., Study on the universality of the normal cloud model, Strategic Study of CAE, 6, 8, pp. 28-34, (2004)
[10] ZHU Q L, BI W, LIU X J, Et al., A batch normalized inference network keeps the KL vanishing away, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2636-2649, (2020)

← 1 2 3 →