An Attribute Graph Embedding Algorithm for Sensing Topological and Attribute Influence

The unsupervised attribute graph embedding technique aims to learn low-dimensional node embedding using neighborhood topology and attribute information under unlabeled data. Current unsupervised models are mostly based on graph self-encoders, but full-batch training limits the scalability of the mod...

Full description

Saved in:
Bibliographic Details
Main Authors: Dongming Chen, Shuyue Zhang, Yumeng Zhao, Mingzhao Xie, Dongqi Wang
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/23/3644
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124138001858560
author Dongming Chen
Shuyue Zhang
Yumeng Zhao
Mingzhao Xie
Dongqi Wang
author_facet Dongming Chen
Shuyue Zhang
Yumeng Zhao
Mingzhao Xie
Dongqi Wang
author_sort Dongming Chen
collection DOAJ
description The unsupervised attribute graph embedding technique aims to learn low-dimensional node embedding using neighborhood topology and attribute information under unlabeled data. Current unsupervised models are mostly based on graph self-encoders, but full-batch training limits the scalability of the model and ignores attribute integrity when reconstructing the topology. In order to solve the above problems while considering the unsupervised learning of the model and full use of node information, this paper proposes a graph neural network architecture based on a graph self-encoder to capture the nonlinearity of the attribute graph data, and an attribute graph embedding algorithm that explicitly models the influence of neighborhood information using a multi-level attention mechanism. Specifically, the proposed algorithm fuses topology information and attribute information using a lightweight sampling strategy, constructs an unbiased graph self-encoder on the sampled graph, implements topology aggregation and attribute aggregation, respectively, models the correlation between topology embedding and attribute embedding, and considers multi-level loss terms.
format Article
id doaj-art-7224a62851564c008b5e2a0541c48ac6
institution Kabale University
issn 2227-7390
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-7224a62851564c008b5e2a0541c48ac62024-12-13T16:27:17ZengMDPI AGMathematics2227-73902024-11-011223364410.3390/math12233644An Attribute Graph Embedding Algorithm for Sensing Topological and Attribute InfluenceDongming Chen0Shuyue Zhang1Yumeng Zhao2Mingzhao Xie3Dongqi Wang4Software College, Northeastern University, Shenyang 110819, ChinaSoftware College, Northeastern University, Shenyang 110819, ChinaSoftware College, Northeastern University, Shenyang 110819, ChinaSoftware College, Northeastern University, Shenyang 110819, ChinaSoftware College, Northeastern University, Shenyang 110819, ChinaThe unsupervised attribute graph embedding technique aims to learn low-dimensional node embedding using neighborhood topology and attribute information under unlabeled data. Current unsupervised models are mostly based on graph self-encoders, but full-batch training limits the scalability of the model and ignores attribute integrity when reconstructing the topology. In order to solve the above problems while considering the unsupervised learning of the model and full use of node information, this paper proposes a graph neural network architecture based on a graph self-encoder to capture the nonlinearity of the attribute graph data, and an attribute graph embedding algorithm that explicitly models the influence of neighborhood information using a multi-level attention mechanism. Specifically, the proposed algorithm fuses topology information and attribute information using a lightweight sampling strategy, constructs an unbiased graph self-encoder on the sampled graph, implements topology aggregation and attribute aggregation, respectively, models the correlation between topology embedding and attribute embedding, and considers multi-level loss terms.https://www.mdpi.com/2227-7390/12/23/3644graph embeddinggraph neural networksattention mechanismsgraph self-encodersattribute graphs
spellingShingle Dongming Chen
Shuyue Zhang
Yumeng Zhao
Mingzhao Xie
Dongqi Wang
An Attribute Graph Embedding Algorithm for Sensing Topological and Attribute Influence
Mathematics
graph embedding
graph neural networks
attention mechanisms
graph self-encoders
attribute graphs
title An Attribute Graph Embedding Algorithm for Sensing Topological and Attribute Influence
title_full An Attribute Graph Embedding Algorithm for Sensing Topological and Attribute Influence
title_fullStr An Attribute Graph Embedding Algorithm for Sensing Topological and Attribute Influence
title_full_unstemmed An Attribute Graph Embedding Algorithm for Sensing Topological and Attribute Influence
title_short An Attribute Graph Embedding Algorithm for Sensing Topological and Attribute Influence
title_sort attribute graph embedding algorithm for sensing topological and attribute influence
topic graph embedding
graph neural networks
attention mechanisms
graph self-encoders
attribute graphs
url https://www.mdpi.com/2227-7390/12/23/3644
work_keys_str_mv AT dongmingchen anattributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence
AT shuyuezhang anattributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence
AT yumengzhao anattributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence
AT mingzhaoxie anattributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence
AT dongqiwang anattributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence
AT dongmingchen attributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence
AT shuyuezhang attributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence
AT yumengzhao attributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence
AT mingzhaoxie attributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence
AT dongqiwang attributegraphembeddingalgorithmforsensingtopologicalandattributeinfluence