SDW2vec: learning structural representations of nodes in weighted networks

Abstract Recent advances in machine learning have prompted researchers to integrate complex network structures into computational frameworks to improve inferential capabilities. Node embedding has become a promising technique in this area. However, challenges persist in accurately representing the s...

Full description

Saved in:
Bibliographic Details
Main Authors: Shu Liu, Masaki Chujyo, Fujio Toriumi
Format: Article
Language:English
Published: SpringerOpen 2025-07-01
Series:Applied Network Science
Subjects:
Online Access:https://doi.org/10.1007/s41109-025-00722-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333139723255808
author Shu Liu
Masaki Chujyo
Fujio Toriumi
author_facet Shu Liu
Masaki Chujyo
Fujio Toriumi
author_sort Shu Liu
collection DOAJ
description Abstract Recent advances in machine learning have prompted researchers to integrate complex network structures into computational frameworks to improve inferential capabilities. Node embedding has become a promising technique in this area. However, challenges persist in accurately representing the structural characteristics of nodes in weighted networks. In this study, we propose SDW2vec, which learns the embeddings of nodes in weighted networks while preserving structural properties. Our proposed methodology addresses these challenges through a multi-scale comparison of link weights among adjacent nodes up to a predefined hop count. This approach facilitates the calculation of distances between nodes’ structural configurations across multiple scales. We subsequently construct weighted multi-layer graphs based on these distance measurements, apply random walks to generate node sequences, and learn the embedding representations using the Skip-gram model. The efficacy of our methodology is validated through both the interpretability of embedding representations in controlled network environments and the structural reproducibility demonstrated in real-world networks.
format Article
id doaj-art-c9b2b7ed026f43c2a01d7e586b9bfaf1
institution Kabale University
issn 2364-8228
language English
publishDate 2025-07-01
publisher SpringerOpen
record_format Article
series Applied Network Science
spelling doaj-art-c9b2b7ed026f43c2a01d7e586b9bfaf12025-08-20T03:45:57ZengSpringerOpenApplied Network Science2364-82282025-07-0110111510.1007/s41109-025-00722-xSDW2vec: learning structural representations of nodes in weighted networksShu Liu0Masaki Chujyo1Fujio Toriumi2Department of Systems Innovation, Faculty of Engineering, The University of TokyoDepartment of Systems Innovation, Faculty of Engineering, The University of TokyoDepartment of Systems Innovation, Faculty of Engineering, The University of TokyoAbstract Recent advances in machine learning have prompted researchers to integrate complex network structures into computational frameworks to improve inferential capabilities. Node embedding has become a promising technique in this area. However, challenges persist in accurately representing the structural characteristics of nodes in weighted networks. In this study, we propose SDW2vec, which learns the embeddings of nodes in weighted networks while preserving structural properties. Our proposed methodology addresses these challenges through a multi-scale comparison of link weights among adjacent nodes up to a predefined hop count. This approach facilitates the calculation of distances between nodes’ structural configurations across multiple scales. We subsequently construct weighted multi-layer graphs based on these distance measurements, apply random walks to generate node sequences, and learn the embedding representations using the Skip-gram model. The efficacy of our methodology is validated through both the interpretability of embedding representations in controlled network environments and the structural reproducibility demonstrated in real-world networks.https://doi.org/10.1007/s41109-025-00722-xRepresentation learningNode embeddingStructural embeddingWeighted networksSigned directed networks
spellingShingle Shu Liu
Masaki Chujyo
Fujio Toriumi
SDW2vec: learning structural representations of nodes in weighted networks
Applied Network Science
Representation learning
Node embedding
Structural embedding
Weighted networks
Signed directed networks
title SDW2vec: learning structural representations of nodes in weighted networks
title_full SDW2vec: learning structural representations of nodes in weighted networks
title_fullStr SDW2vec: learning structural representations of nodes in weighted networks
title_full_unstemmed SDW2vec: learning structural representations of nodes in weighted networks
title_short SDW2vec: learning structural representations of nodes in weighted networks
title_sort sdw2vec learning structural representations of nodes in weighted networks
topic Representation learning
Node embedding
Structural embedding
Weighted networks
Signed directed networks
url https://doi.org/10.1007/s41109-025-00722-x
work_keys_str_mv AT shuliu sdw2veclearningstructuralrepresentationsofnodesinweightednetworks
AT masakichujyo sdw2veclearningstructuralrepresentationsofnodesinweightednetworks
AT fujiotoriumi sdw2veclearningstructuralrepresentationsofnodesinweightednetworks