DeeWaNA: An Unsupervised Network Representation Learning Framework Integrating Deepwalk and Neighborhood Aggregation for Node Classification

This paper introduces DeeWaNA, an unsupervised network representation learning framework that unifies random walk strategies and neighborhood aggregation mechanisms to improve node classification performance. Unlike existing methods that treat these two paradigms separately, our approach integrates...

Full description

Saved in:
Bibliographic Details
Main Authors: Xin Xu, Xinya Lu, Jianan Wang
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/27/3/322
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204774556762112
author Xin Xu
Xinya Lu
Jianan Wang
author_facet Xin Xu
Xinya Lu
Jianan Wang
author_sort Xin Xu
collection DOAJ
description This paper introduces DeeWaNA, an unsupervised network representation learning framework that unifies random walk strategies and neighborhood aggregation mechanisms to improve node classification performance. Unlike existing methods that treat these two paradigms separately, our approach integrates them into a cohesive model, addressing limitations in structural feature extraction and neighborhood relationship modeling. DeeWaNA first leverages DeepWalk to capture global structural information and then employs an attention-based weighting mechanism to refine neighborhood relationships through a novel distance metric. Finally, a weighted aggregation operator fuses these representations into a unified low-dimensional space. By bridging the gap between random-walk-based and neural-network-based techniques, our framework enhances representation quality and improves classification accuracy. Extensive evaluations on real-world networks demonstrate that DeeWaNA outperforms four widely used unsupervised network representation learning methods, underscoring its effectiveness and broader applicability.
format Article
id doaj-art-4976c645894f4b4f8765c14064e4a75e
institution OA Journals
issn 1099-4300
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-4976c645894f4b4f8765c14064e4a75e2025-08-20T02:11:14ZengMDPI AGEntropy1099-43002025-03-0127332210.3390/e27030322DeeWaNA: An Unsupervised Network Representation Learning Framework Integrating Deepwalk and Neighborhood Aggregation for Node ClassificationXin Xu0Xinya Lu1Jianan Wang2School of Media Science, Northeast Normal University, Jingye Street 2555, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, Jingye Street 2555, Changchun 130117, ChinaSchool of Physics, Northeast Normal University, Renmin Street 5268, Changchun 130024, ChinaThis paper introduces DeeWaNA, an unsupervised network representation learning framework that unifies random walk strategies and neighborhood aggregation mechanisms to improve node classification performance. Unlike existing methods that treat these two paradigms separately, our approach integrates them into a cohesive model, addressing limitations in structural feature extraction and neighborhood relationship modeling. DeeWaNA first leverages DeepWalk to capture global structural information and then employs an attention-based weighting mechanism to refine neighborhood relationships through a novel distance metric. Finally, a weighted aggregation operator fuses these representations into a unified low-dimensional space. By bridging the gap between random-walk-based and neural-network-based techniques, our framework enhances representation quality and improves classification accuracy. Extensive evaluations on real-world networks demonstrate that DeeWaNA outperforms four widely used unsupervised network representation learning methods, underscoring its effectiveness and broader applicability.https://www.mdpi.com/1099-4300/27/3/322unsupervised network representation learningnode classificationrandom walkneighborhood aggregationgraph embedding
spellingShingle Xin Xu
Xinya Lu
Jianan Wang
DeeWaNA: An Unsupervised Network Representation Learning Framework Integrating Deepwalk and Neighborhood Aggregation for Node Classification
Entropy
unsupervised network representation learning
node classification
random walk
neighborhood aggregation
graph embedding
title DeeWaNA: An Unsupervised Network Representation Learning Framework Integrating Deepwalk and Neighborhood Aggregation for Node Classification
title_full DeeWaNA: An Unsupervised Network Representation Learning Framework Integrating Deepwalk and Neighborhood Aggregation for Node Classification
title_fullStr DeeWaNA: An Unsupervised Network Representation Learning Framework Integrating Deepwalk and Neighborhood Aggregation for Node Classification
title_full_unstemmed DeeWaNA: An Unsupervised Network Representation Learning Framework Integrating Deepwalk and Neighborhood Aggregation for Node Classification
title_short DeeWaNA: An Unsupervised Network Representation Learning Framework Integrating Deepwalk and Neighborhood Aggregation for Node Classification
title_sort deewana an unsupervised network representation learning framework integrating deepwalk and neighborhood aggregation for node classification
topic unsupervised network representation learning
node classification
random walk
neighborhood aggregation
graph embedding
url https://www.mdpi.com/1099-4300/27/3/322
work_keys_str_mv AT xinxu deewanaanunsupervisednetworkrepresentationlearningframeworkintegratingdeepwalkandneighborhoodaggregationfornodeclassification
AT xinyalu deewanaanunsupervisednetworkrepresentationlearningframeworkintegratingdeepwalkandneighborhoodaggregationfornodeclassification
AT jiananwang deewanaanunsupervisednetworkrepresentationlearningframeworkintegratingdeepwalkandneighborhoodaggregationfornodeclassification