An Unsupervised Learning Method for Attributed Network Based on Non-Euclidean Geometry
Many real-world networks can be modeled as attributed networks, where nodes are affiliated with attributes. When we implement attributed network embedding, we need to face two types of heterogeneous information, namely, structural information and attribute information. The structural information of...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-05-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/13/5/905 |
_version_ | 1797533476228956160 |
---|---|
author | Wei Wu Guangmin Hu Fucai Yu |
author_facet | Wei Wu Guangmin Hu Fucai Yu |
author_sort | Wei Wu |
collection | DOAJ |
description | Many real-world networks can be modeled as attributed networks, where nodes are affiliated with attributes. When we implement attributed network embedding, we need to face two types of heterogeneous information, namely, structural information and attribute information. The structural information of undirected networks is usually expressed as a symmetric adjacency matrix. Network embedding learning is to utilize the above information to learn the vector representations of nodes in the network. How to integrate these two types of heterogeneous information to improve the performance of network embedding is a challenge. Most of the current approaches embed the networks in Euclidean spaces, but the networks themselves are non-Euclidean. As a consequence, the geometric differences between the embedded space and the underlying space of the network will affect the performance of the network embedding. According to the non-Euclidean geometry of networks, this paper proposes an attributed network embedding framework based on hyperbolic geometry and the Ricci curvature, namely, RHAE. Our method consists of two modules: (1) the first module is an autoencoder module in which each layer is provided with a network information aggregation layer based on the Ricci curvature and an embedding layer based on hyperbolic geometry; (2) the second module is a skip-gram module in which the random walk is based on the Ricci curvature. These two modules are based on non-Euclidean geometry, but they fuse the topology information and attribute information in the network from different angles. Experimental results on some benchmark datasets show that our approach outperforms the baselines. |
first_indexed | 2024-03-10T11:15:06Z |
format | Article |
id | doaj.art-50024785cfb5480091a6538668db53f1 |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-03-10T11:15:06Z |
publishDate | 2021-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-50024785cfb5480091a6538668db53f12023-11-21T20:28:05ZengMDPI AGSymmetry2073-89942021-05-0113590510.3390/sym13050905An Unsupervised Learning Method for Attributed Network Based on Non-Euclidean GeometryWei Wu0Guangmin Hu1Fucai Yu2School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaMany real-world networks can be modeled as attributed networks, where nodes are affiliated with attributes. When we implement attributed network embedding, we need to face two types of heterogeneous information, namely, structural information and attribute information. The structural information of undirected networks is usually expressed as a symmetric adjacency matrix. Network embedding learning is to utilize the above information to learn the vector representations of nodes in the network. How to integrate these two types of heterogeneous information to improve the performance of network embedding is a challenge. Most of the current approaches embed the networks in Euclidean spaces, but the networks themselves are non-Euclidean. As a consequence, the geometric differences between the embedded space and the underlying space of the network will affect the performance of the network embedding. According to the non-Euclidean geometry of networks, this paper proposes an attributed network embedding framework based on hyperbolic geometry and the Ricci curvature, namely, RHAE. Our method consists of two modules: (1) the first module is an autoencoder module in which each layer is provided with a network information aggregation layer based on the Ricci curvature and an embedding layer based on hyperbolic geometry; (2) the second module is a skip-gram module in which the random walk is based on the Ricci curvature. These two modules are based on non-Euclidean geometry, but they fuse the topology information and attribute information in the network from different angles. Experimental results on some benchmark datasets show that our approach outperforms the baselines.https://www.mdpi.com/2073-8994/13/5/905hyperbolic geometryattributed networkRicci curvaturesymmetric matrix |
spellingShingle | Wei Wu Guangmin Hu Fucai Yu An Unsupervised Learning Method for Attributed Network Based on Non-Euclidean Geometry Symmetry hyperbolic geometry attributed network Ricci curvature symmetric matrix |
title | An Unsupervised Learning Method for Attributed Network Based on Non-Euclidean Geometry |
title_full | An Unsupervised Learning Method for Attributed Network Based on Non-Euclidean Geometry |
title_fullStr | An Unsupervised Learning Method for Attributed Network Based on Non-Euclidean Geometry |
title_full_unstemmed | An Unsupervised Learning Method for Attributed Network Based on Non-Euclidean Geometry |
title_short | An Unsupervised Learning Method for Attributed Network Based on Non-Euclidean Geometry |
title_sort | unsupervised learning method for attributed network based on non euclidean geometry |
topic | hyperbolic geometry attributed network Ricci curvature symmetric matrix |
url | https://www.mdpi.com/2073-8994/13/5/905 |
work_keys_str_mv | AT weiwu anunsupervisedlearningmethodforattributednetworkbasedonnoneuclideangeometry AT guangminhu anunsupervisedlearningmethodforattributednetworkbasedonnoneuclideangeometry AT fucaiyu anunsupervisedlearningmethodforattributednetworkbasedonnoneuclideangeometry AT weiwu unsupervisedlearningmethodforattributednetworkbasedonnoneuclideangeometry AT guangminhu unsupervisedlearningmethodforattributednetworkbasedonnoneuclideangeometry AT fucaiyu unsupervisedlearningmethodforattributednetworkbasedonnoneuclideangeometry |