Cargando…

Graph Autoencoder with Preserving Node Attribute Similarity

The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservatio...

Descripción completa

Detalles Bibliográficos
Autores principales: Lin, Mugang, Wen, Kunhui, Zhu, Xuanying, Zhao, Huihuang, Sun, Xianfang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10138145/
https://www.ncbi.nlm.nih.gov/pubmed/37190356
http://dx.doi.org/10.3390/e25040567
_version_ 1785032637423812608
author Lin, Mugang
Wen, Kunhui
Zhu, Xuanying
Zhao, Huihuang
Sun, Xianfang
author_facet Lin, Mugang
Wen, Kunhui
Zhu, Xuanying
Zhao, Huihuang
Sun, Xianfang
author_sort Lin, Mugang
collection PubMed
description The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservation of the attribute information of nodes. Thus, the node attributes cannot be fully learned and the ability of the GAE to learn higher-quality representations is weakened. To address the issue, this paper proposes a novel GAE model that preserves node attribute similarity. The structural graph and the attribute neighbor graph, which is constructed based on the attribute similarity between nodes, are integrated as the encoder input using an effective fusion strategy. In the encoder, the attributes of the nodes can be aggregated both in their structural neighborhood and by their attribute similarity in their attribute neighborhood. This allows performing the fusion of the structural and node attribute information in the node representation by sharing the same encoder. In the decoder module, the adjacency matrix and the attribute similarity matrix of the nodes are reconstructed using dual decoders. The cross-entropy loss of the reconstructed adjacency matrix and the mean-squared error loss of the reconstructed node attribute similarity matrix are used to update the model parameters and ensure that the node representation preserves the original structural and node attribute similarity information. Extensive experiments on three citation networks show that the proposed method outperforms state-of-the-art algorithms in link prediction and node clustering tasks.
format Online
Article
Text
id pubmed-10138145
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-101381452023-04-28 Graph Autoencoder with Preserving Node Attribute Similarity Lin, Mugang Wen, Kunhui Zhu, Xuanying Zhao, Huihuang Sun, Xianfang Entropy (Basel) Article The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservation of the attribute information of nodes. Thus, the node attributes cannot be fully learned and the ability of the GAE to learn higher-quality representations is weakened. To address the issue, this paper proposes a novel GAE model that preserves node attribute similarity. The structural graph and the attribute neighbor graph, which is constructed based on the attribute similarity between nodes, are integrated as the encoder input using an effective fusion strategy. In the encoder, the attributes of the nodes can be aggregated both in their structural neighborhood and by their attribute similarity in their attribute neighborhood. This allows performing the fusion of the structural and node attribute information in the node representation by sharing the same encoder. In the decoder module, the adjacency matrix and the attribute similarity matrix of the nodes are reconstructed using dual decoders. The cross-entropy loss of the reconstructed adjacency matrix and the mean-squared error loss of the reconstructed node attribute similarity matrix are used to update the model parameters and ensure that the node representation preserves the original structural and node attribute similarity information. Extensive experiments on three citation networks show that the proposed method outperforms state-of-the-art algorithms in link prediction and node clustering tasks. MDPI 2023-03-26 /pmc/articles/PMC10138145/ /pubmed/37190356 http://dx.doi.org/10.3390/e25040567 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Lin, Mugang
Wen, Kunhui
Zhu, Xuanying
Zhao, Huihuang
Sun, Xianfang
Graph Autoencoder with Preserving Node Attribute Similarity
title Graph Autoencoder with Preserving Node Attribute Similarity
title_full Graph Autoencoder with Preserving Node Attribute Similarity
title_fullStr Graph Autoencoder with Preserving Node Attribute Similarity
title_full_unstemmed Graph Autoencoder with Preserving Node Attribute Similarity
title_short Graph Autoencoder with Preserving Node Attribute Similarity
title_sort graph autoencoder with preserving node attribute similarity
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10138145/
https://www.ncbi.nlm.nih.gov/pubmed/37190356
http://dx.doi.org/10.3390/e25040567
work_keys_str_mv AT linmugang graphautoencoderwithpreservingnodeattributesimilarity
AT wenkunhui graphautoencoderwithpreservingnodeattributesimilarity
AT zhuxuanying graphautoencoderwithpreservingnodeattributesimilarity
AT zhaohuihuang graphautoencoderwithpreservingnodeattributesimilarity
AT sunxianfang graphautoencoderwithpreservingnodeattributesimilarity