Graph signal processing techniques for machine learning optimization

Graph Signal Processing (GSP) offers a flexible framework for extending classical signal processing techniques, such as filtering and sampling, to irregular domains like social networks. In this context, the Q-GFT, a generalization of the Graph Fourier Transform (GFT) that incorporates a non-trivial...

ver descrição completa

Detalhes bibliográficos
Autor: Beaus Iranzo, Pablo
Formato: tesis de maestría
Fecha de publicación:2024
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/418112
Acesso em linha:https://hdl.handle.net/2117/418112
Access Level:acceso abierto
Palavra-chave:Machine learning
Neural networks (Computer science)
Signal processing
graph
graph signal processing
machine learning
neural networks
Aprenentatge automàtic
Xarxes neuronals (Informàtica)
Tractament del senyal
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal
id ES_4e37893a6593ad9f2c43d3b04cf5c08b
oai_identifier_str oai:upcommons.upc.edu:2117/418112
network_acronym_str ES
network_name_str España
repository_id_str
spelling Graph signal processing techniques for machine learning optimizationBeaus Iranzo, PabloMachine learningNeural networks (Computer science)Signal processinggraphgraph signal processingmachine learningneural networksAprenentatge automàticXarxes neuronals (Informàtica)Tractament del senyalÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyalGraph Signal Processing (GSP) offers a flexible framework for extending classical signal processing techniques, such as filtering and sampling, to irregular domains like social networks. In this context, the Q-GFT, a generalization of the Graph Fourier Transform (GFT) that incorporates a non-trivial inner product, was introduced to provide a more flexible analysis of graph signals. The Q-GFT brings additional flexibility through its variation operator, graph partitioning strategies, and modification of spectral properties. In this thesis, we explore the integration of the Q-GFT with graph neural networks (GNNs) for node classification tasks. We investigate the impact of Q-GFT and evaluate their effect on well-known GNN architectures such as Graph Convolutional Networks (GCNs) and GraphSAGE. Results provide valuable insights into the interaction between graph partitioning strategies and neural networks, showing how energy concentration patterns from different Q-based Graph Fourier Transforms (Q-GFT) correlate with model performance. While most models did not outperform the baseline, using ground-truth labels for the Fully Balanced max-cut did, suggesting potential for new partitioning methods to advance graph machine learning.Universitat Politècnica de CatalunyaMarqués Acosta, Fernando20242024-10-2920242024-11-15master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/418112reponame: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:2117/4181122026-05-27T15:37:01Z
dc.title.none.fl_str_mv Graph signal processing techniques for machine learning optimization
title Graph signal processing techniques for machine learning optimization
spellingShingle Graph signal processing techniques for machine learning optimization
Beaus Iranzo, Pablo
Machine learning
Neural networks (Computer science)
Signal processing
graph
graph signal processing
machine learning
neural networks
Aprenentatge automàtic
Xarxes neuronals (Informàtica)
Tractament del senyal
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal
title_short Graph signal processing techniques for machine learning optimization
title_full Graph signal processing techniques for machine learning optimization
title_fullStr Graph signal processing techniques for machine learning optimization
title_full_unstemmed Graph signal processing techniques for machine learning optimization
title_sort Graph signal processing techniques for machine learning optimization
dc.creator.none.fl_str_mv Beaus Iranzo, Pablo
author Beaus Iranzo, Pablo
author_facet Beaus Iranzo, Pablo
author_role author
dc.contributor.none.fl_str_mv Marqués Acosta, Fernando
dc.subject.none.fl_str_mv Machine learning
Neural networks (Computer science)
Signal processing
graph
graph signal processing
machine learning
neural networks
Aprenentatge automàtic
Xarxes neuronals (Informàtica)
Tractament del senyal
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal
topic Machine learning
Neural networks (Computer science)
Signal processing
graph
graph signal processing
machine learning
neural networks
Aprenentatge automàtic
Xarxes neuronals (Informàtica)
Tractament del senyal
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal
description Graph Signal Processing (GSP) offers a flexible framework for extending classical signal processing techniques, such as filtering and sampling, to irregular domains like social networks. In this context, the Q-GFT, a generalization of the Graph Fourier Transform (GFT) that incorporates a non-trivial inner product, was introduced to provide a more flexible analysis of graph signals. The Q-GFT brings additional flexibility through its variation operator, graph partitioning strategies, and modification of spectral properties. In this thesis, we explore the integration of the Q-GFT with graph neural networks (GNNs) for node classification tasks. We investigate the impact of Q-GFT and evaluate their effect on well-known GNN architectures such as Graph Convolutional Networks (GCNs) and GraphSAGE. Results provide valuable insights into the interaction between graph partitioning strategies and neural networks, showing how energy concentration patterns from different Q-based Graph Fourier Transforms (Q-GFT) correlate with model performance. While most models did not outperform the baseline, using ground-truth labels for the Fully Balanced max-cut did, suggesting potential for new partitioning methods to advance graph machine learning.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-10-29
2024
2024-11-15
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/2117/418112
url https://hdl.handle.net/2117/418112
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_ 1869407741752115200
score 15.812455

Registos relacionados