Towards a Data-Driven Graph Neural Network Model Selection

Graph Neural Networks (GNNs) have achieved great success in solving many machine learning tasks, and many different neural architectures have been proposed over the past few years. However, the lack of robust public benchmarks hinders the assessment of GNN architectures, which has made most research...

Descripción completa

Detalles Bibliográficos
Autor: Higueras Serrano, Raúl
Tipo de recurso: tesis de maestría
Fecha de publicación:2024
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/411416
Acceso en línea:https://hdl.handle.net/2117/411416
Access Level:acceso abierto
Palabra clave:Neural networks (Computer science)
Machine learning
Graph theory
graph neural networks
neural networks
meta-learning
machine learning
deep learning
artificial intelligence
model selection
neural architecture search
graph theory
graph model
graph generator
data science
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Grafs, Teoria de
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
id ES_19028f2e2000ee44e23e3e8013f85ffc
oai_identifier_str oai:upcommons.upc.edu:2117/411416
network_acronym_str ES
network_name_str España
repository_id_str
spelling Towards a Data-Driven Graph Neural Network Model SelectionTowards Data-Driven Graph Neural Network Model SelectionHigueras Serrano, RaúlNeural networks (Computer science)Machine learningGraph theorygraph neural networksneural networksmeta-learningmachine learningdeep learningartificial intelligencemodel selectionneural architecture searchgraph theorygraph modelgraph generatordata scienceXarxes neuronals (Informàtica)Aprenentatge automàticGrafs, Teoria deÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàticGraph Neural Networks (GNNs) have achieved great success in solving many machine learning tasks, and many different neural architectures have been proposed over the past few years. However, the lack of robust public benchmarks hinders the assessment of GNN architectures, which has made most research papers rely on the same 5-10 datasets. Our first contribution is Graphlaxy++, a novel generative graph learning model designed to emulate GNN performance and that can be used to generate artificial benchmarks with user-defined metrics. Leveraging Graphlaxy++, we generate a diverse synthetic graph dataset that serves as input to a predictive statistical model that can predict the performance of GNNs. This model is able to successfully predict the relative performance of 4 different architectures: GCN, GAT, GIN, and MLP. The predictive capacity of this model offers potential applications in speeding up neural architecture searches and optimizing graph modeling strategies.Universitat Politècnica de CatalunyaAbadal Cavallé, SergiWassington, Axel20242024-01-2620242024-07-10master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/411416reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/4114162026-05-27T15:37:01Z
dc.title.none.fl_str_mv Towards a Data-Driven Graph Neural Network Model Selection
Towards Data-Driven Graph Neural Network Model Selection
title Towards a Data-Driven Graph Neural Network Model Selection
spellingShingle Towards a Data-Driven Graph Neural Network Model Selection
Higueras Serrano, Raúl
Neural networks (Computer science)
Machine learning
Graph theory
graph neural networks
neural networks
meta-learning
machine learning
deep learning
artificial intelligence
model selection
neural architecture search
graph theory
graph model
graph generator
data science
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Grafs, Teoria de
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
title_short Towards a Data-Driven Graph Neural Network Model Selection
title_full Towards a Data-Driven Graph Neural Network Model Selection
title_fullStr Towards a Data-Driven Graph Neural Network Model Selection
title_full_unstemmed Towards a Data-Driven Graph Neural Network Model Selection
title_sort Towards a Data-Driven Graph Neural Network Model Selection
dc.creator.none.fl_str_mv Higueras Serrano, Raúl
author Higueras Serrano, Raúl
author_facet Higueras Serrano, Raúl
author_role author
dc.contributor.none.fl_str_mv Abadal Cavallé, Sergi
Wassington, Axel
dc.subject.none.fl_str_mv Neural networks (Computer science)
Machine learning
Graph theory
graph neural networks
neural networks
meta-learning
machine learning
deep learning
artificial intelligence
model selection
neural architecture search
graph theory
graph model
graph generator
data science
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Grafs, Teoria de
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
topic Neural networks (Computer science)
Machine learning
Graph theory
graph neural networks
neural networks
meta-learning
machine learning
deep learning
artificial intelligence
model selection
neural architecture search
graph theory
graph model
graph generator
data science
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Grafs, Teoria de
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
description Graph Neural Networks (GNNs) have achieved great success in solving many machine learning tasks, and many different neural architectures have been proposed over the past few years. However, the lack of robust public benchmarks hinders the assessment of GNN architectures, which has made most research papers rely on the same 5-10 datasets. Our first contribution is Graphlaxy++, a novel generative graph learning model designed to emulate GNN performance and that can be used to generate artificial benchmarks with user-defined metrics. Leveraging Graphlaxy++, we generate a diverse synthetic graph dataset that serves as input to a predictive statistical model that can predict the performance of GNNs. This model is able to successfully predict the relative performance of 4 different architectures: GCN, GAT, GIN, and MLP. The predictive capacity of this model offers potential applications in speeding up neural architecture searches and optimizing graph modeling strategies.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-01-26
2024
2024-07-10
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/411416
url https://hdl.handle.net/2117/411416
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404020187070465
score 15,811543

Similares en LA Referencia