Towards Semantically-Rich Spatial Network Representation Learning via Automated Feature Topic Pairing

Simple item page
dc.contributor.authorWang, Dongjieen
dc.contributor.authorLiu, Kunpengen
dc.contributor.authorMohaisen, Daviden
dc.contributor.authorWang, Pengyangen
dc.contributor.authorLu, Chang-Tienen
dc.contributor.authorFu, Yanjieen
dc.date.accessioned2024-02-23T14:34:25Zen
dc.date.available2024-02-23T14:34:25Zen
dc.date.issued2021-10-20en
dc.description.abstractAutomated characterization of spatial data is a kind of critical geographical intelligence. As an emerging technique for characterization, spatial Representation Learning (SRL) uses deep neural networks (DNNs) to learn non-linear embedded features of spatial data for characterization. However, SRL extracts features by internal layers of DNNs, and thus suffers from lacking semantic labels. Texts of spatial entities, on the other hand, provide semantic understanding of latent feature labels, but is insensible to deep SRL models. How can we teach a SRL model to discover appropriate topic labels in texts and pair learned features with the labels? This paper formulates a new problem: feature-topic pairing, and proposes a novel Particle Swarm Optimization (PSO) based deep learning framework. Specifically, we formulate the feature-topic pairing problem into an automated alignment task between 1) a latent embedding feature space and 2) a textual semantic topic space. We decompose the alignment of the two spaces into: 1) point-wise alignment, denoting the correlation between a topic distribution and an embedding vector; 2) pair-wise alignment, denoting the consistency between a feature-feature similarity matrix and a topic-topic similarity matrix. We design a PSO based solver to simultaneously select an optimal set of topics and learn corresponding features based on the selected topics. We develop a closed loop algorithm to iterate between 1) minimizing losses of representation reconstruction and feature-topic alignment and 2) searching the best topics. Finally, we present extensive experiments to demonstrate the enhanced performance of our method.en
dc.description.versionPublished versionen
dc.format.extent16 page(s)en
dc.format.mimetypeapplication/pdfen
dc.identifierARTN 762899 (Article number)en
dc.identifier.doihttps://doi.org/10.3389/fdata.2021.762899en
dc.identifier.eissn2624-909Xen
dc.identifier.issn2624-909Xen
dc.identifier.orcidLu, Chang Tien [0000-0003-3675-0199]en
dc.identifier.otherPMC8564394en
dc.identifier.other762899 (PII)en
dc.identifier.pmid34746772en
dc.identifier.urihttps://hdl.handle.net/10919/118119en
dc.identifier.volume4en
dc.language.isoenen
dc.publisherFrontiersen
dc.relation.urihttps://www.ncbi.nlm.nih.gov/pubmed/34746772en
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectfeature-topic pairingen
dc.subjectsemantic spaceen
dc.subjectspatial spaceen
dc.subjectspatial representation learningen
dc.subjectspatial graphen
dc.titleTowards Semantically-Rich Spatial Network Representation Learning <i>via</i> Automated Feature Topic Pairingen
dc.title.serialFrontiers in Big Dataen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.otherArticleen
dc.type.otherJournalen
dcterms.dateAccepted2021-09-20en
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/All T&R Facultyen
pubs.organisational-group/Virginia Tech/Innovation Campusen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Towards Semantically-Rich Spatial Network Representation Learning iviai Automated Feature Topic Pairing.pdf
Size:
2.7 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download
License bundle
Now showing 1 - 1 of 1
Name:
license.txt
Size:
1.5 KB
Format:
Plain Text
Description:
Download

Collections

All Faculty Deposits
Scholarly Works, Computer Science