A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications

Autores
Borzone, Eugenio; Di Persia, Leandro Ezequiel; Gerard, Matias Fernando
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
This paper presents a novelgraph-based deep learning model for tasks involving relations between two nodes (edge-centric tasks), where the focuslies on predicting relationships and interactions between pairs of nodes rather than node properties themselves. This model combines supervised and self-supervisedlearning, taking into account for the loss function the embeddings learned and patterns with and without ground truth. Additionally it incorporates an attention mechanism that leveragesboth node and edge features. The architecture, trained end-to-end, comprises two primary components: embedding generation and prediction. First, a graph neural network (GNN) transform raw node features into dense, low-dimensional embeddings, incorporating edge attributes. Then, a feedforward neural model processes the node embeddings to produce the final output. Experiments demonstrate that our model matches or exceeds existing methods for protein-protein interactions prediction and Gene Ontology (GO) terms prediction. The model also performs effectively with one-hot encoding for node features, providing a solution for the previously unsolved problem of predicting similarity between compounds with unknown structures.
Fil: Borzone, Eugenio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Di Persia, Leandro Ezequiel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Gerard, Matias Fernando. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Materia
GRAPH NEURAL NETWORKS
NODE EMBEDDINGS
PROPERTY PREDICTION
EDGE REGRESSION
EDGE CLASSIFICATION
LINK PREDICTION
ATTENTION MECHANISM
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/281375
Acceder
id CONICETDig_fd5a1c724eba61c5ea2b466c182ca0ae
oai_identifier_str oai:ri.conicet.gov.ar:11336/281375
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric ApplicationsBorzone, EugenioDi Persia, Leandro EzequielGerard, Matias FernandoGRAPH NEURAL NETWORKSNODE EMBEDDINGSPROPERTY PREDICTIONEDGE REGRESSIONEDGE CLASSIFICATIONLINK PREDICTIONATTENTION MECHANISMhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1This paper presents a novelgraph-based deep learning model for tasks involving relations between two nodes (edge-centric tasks), where the focuslies on predicting relationships and interactions between pairs of nodes rather than node properties themselves. This model combines supervised and self-supervisedlearning, taking into account for the loss function the embeddings learned and patterns with and without ground truth. Additionally it incorporates an attention mechanism that leveragesboth node and edge features. The architecture, trained end-to-end, comprises two primary components: embedding generation and prediction. First, a graph neural network (GNN) transform raw node features into dense, low-dimensional embeddings, incorporating edge attributes. Then, a feedforward neural model processes the node embeddings to produce the final output. Experiments demonstrate that our model matches or exceeds existing methods for protein-protein interactions prediction and Gene Ontology (GO) terms prediction. The model also performs effectively with one-hot encoding for node features, providing a solution for the previously unsolved problem of predicting similarity between compounds with unknown structures.Fil: Borzone, Eugenio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaFil: Di Persia, Leandro Ezequiel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaFil: Gerard, Matias Fernando. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaInstitute of Electrical and Electronics Engineers2025-09info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/281375Borzone, Eugenio; Di Persia, Leandro Ezequiel; Gerard, Matias Fernando; A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications; Institute of Electrical and Electronics Engineers; IEEE Transactions on Signal and Information Processing over Networks; 11; 9-2025; 1268-12772373-776XCONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://ieeexplore.ieee.org/document/11168281/info:eu-repo/semantics/altIdentifier/doi/10.1109/TSIPN.2025.3611172info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-02-26T10:29:36Zoai:ri.conicet.gov.ar:11336/281375instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982026-02-26 10:29:37.234CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications
title A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications
spellingShingle A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications
Borzone, Eugenio
GRAPH NEURAL NETWORKS
NODE EMBEDDINGS
PROPERTY PREDICTION
EDGE REGRESSION
EDGE CLASSIFICATION
LINK PREDICTION
ATTENTION MECHANISM
title_short A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications
title_full A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications
title_fullStr A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications
title_full_unstemmed A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications
title_sort A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications
dc.creator.none.fl_str_mv Borzone, Eugenio
Di Persia, Leandro Ezequiel
Gerard, Matias Fernando
author Borzone, Eugenio
author_facet Borzone, Eugenio
Di Persia, Leandro Ezequiel
Gerard, Matias Fernando
author_role author
author2 Di Persia, Leandro Ezequiel
Gerard, Matias Fernando
author2_role author
author
dc.subject.none.fl_str_mv GRAPH NEURAL NETWORKS
NODE EMBEDDINGS
PROPERTY PREDICTION
EDGE REGRESSION
EDGE CLASSIFICATION
LINK PREDICTION
ATTENTION MECHANISM
topic GRAPH NEURAL NETWORKS
NODE EMBEDDINGS
PROPERTY PREDICTION
EDGE REGRESSION
EDGE CLASSIFICATION
LINK PREDICTION
ATTENTION MECHANISM
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv This paper presents a novelgraph-based deep learning model for tasks involving relations between two nodes (edge-centric tasks), where the focuslies on predicting relationships and interactions between pairs of nodes rather than node properties themselves. This model combines supervised and self-supervisedlearning, taking into account for the loss function the embeddings learned and patterns with and without ground truth. Additionally it incorporates an attention mechanism that leveragesboth node and edge features. The architecture, trained end-to-end, comprises two primary components: embedding generation and prediction. First, a graph neural network (GNN) transform raw node features into dense, low-dimensional embeddings, incorporating edge attributes. Then, a feedforward neural model processes the node embeddings to produce the final output. Experiments demonstrate that our model matches or exceeds existing methods for protein-protein interactions prediction and Gene Ontology (GO) terms prediction. The model also performs effectively with one-hot encoding for node features, providing a solution for the previously unsolved problem of predicting similarity between compounds with unknown structures.
Fil: Borzone, Eugenio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Di Persia, Leandro Ezequiel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Gerard, Matias Fernando. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
description This paper presents a novelgraph-based deep learning model for tasks involving relations between two nodes (edge-centric tasks), where the focuslies on predicting relationships and interactions between pairs of nodes rather than node properties themselves. This model combines supervised and self-supervisedlearning, taking into account for the loss function the embeddings learned and patterns with and without ground truth. Additionally it incorporates an attention mechanism that leveragesboth node and edge features. The architecture, trained end-to-end, comprises two primary components: embedding generation and prediction. First, a graph neural network (GNN) transform raw node features into dense, low-dimensional embeddings, incorporating edge attributes. Then, a feedforward neural model processes the node embeddings to produce the final output. Experiments demonstrate that our model matches or exceeds existing methods for protein-protein interactions prediction and Gene Ontology (GO) terms prediction. The model also performs effectively with one-hot encoding for node features, providing a solution for the previously unsolved problem of predicting similarity between compounds with unknown structures.
publishDate 2025
dc.date.none.fl_str_mv 2025-09
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/281375
Borzone, Eugenio; Di Persia, Leandro Ezequiel; Gerard, Matias Fernando; A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications; Institute of Electrical and Electronics Engineers; IEEE Transactions on Signal and Information Processing over Networks; 11; 9-2025; 1268-1277
2373-776X
CONICET Digital
CONICET
url http://hdl.handle.net/11336/281375
identifier_str_mv Borzone, Eugenio; Di Persia, Leandro Ezequiel; Gerard, Matias Fernando; A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications; Institute of Electrical and Electronics Engineers; IEEE Transactions on Signal and Information Processing over Networks; 11; 9-2025; 1268-1277
2373-776X
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://ieeexplore.ieee.org/document/11168281/
info:eu-repo/semantics/altIdentifier/doi/10.1109/TSIPN.2025.3611172
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1858305997505822720
score 12.665996

Publicaciones similares