Graph representations for reinforcement learning

Autores
Schab, Esteban; Casanova, Carlos; Piccoli, Fabiana
Año de publicación
2024
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Graph analysis is becoming increasingly important due to the expressive power of graph models and the efficient algorithms available for processing them. Reinforcement Learning is one domain that could benefit from advancements in graph analysis, given that a learning agent may be integrated into an environment that can be represented as a graph. Nevertheless, the structural irregularity of graphs and the lack of prior labels make it difficult to integrate such a model into modern Reinforcement Learning frameworks that rely on artificial neural networks. Graph embedding enables the learning of low-dimensional vector representations that are more suited for machine learning algorithms, while retaining essential graph features. This paper presents a framework for evaluating graph embedding algorithms and their ability to preserve the structure and relevant features of graphs by means of an internal validation metric, without resorting to subsequent tasks that require labels for training. Based on this framework, three defined algorithms that meet the necessary requirements for solving a specific problem of Reinforcement Learning in graphs are selected, analyzed, and compared. These algorithms are Graph2Vec, GL2Vec, and Wavelet Characteristics, with the latter two demonstrating superior performance.
El análisis de grafos es un tópico emergente debido a la expresividad de los modelos basados en grafos y al desarrollo de algoritmos para su procesamiento. Un área que puede beneficiarse de estos avances es el aprendizaje por refuerzo, dado que un agente de aprendizaje puede estar imnerso en un entorno modelable como un grafo. Sin embargo, tanto la irregularidad de las características estructurales de los grafos como la ausencia de etiquetas a priori dificultan la incorporación de un modelo de este tipo en los marcos modernos de Aprendizaje por Refuerzo basados en redes neuronales artificiales. En este sentido, los embeddings de grafos permiten aprender representaciones vectoriales de baja dimensión, más adecuadas para los algoritmos de aprendizaje automático, preservando al mismo tiempo las características clave de los grafos. Proponemos un marco para evaluar algoritmos de Graph Embedding y su capacidad para preservar la estructura y características relevantes de los grafos mediante una métrica de validación interna, sin recurrir a tareas posteriores que requieran etiquetas para el entrenamiento. Aplicando este marco con un problema concreto, se seleccionan, analizan y comparan tres algoritmos que cumplen los requisitos necesarios: Graph2Vec, GL2Vec y Wavelet Characteristics, donde los dos últimos muestran un mejor comportamiento.
Facultad de Informática
Materia
Ciencias Informáticas
Computational Intelligence
Reinforcement Learning
Graph Embeddings
unsupervised GRL
Whole Graph Embedding
Inteligencia Computacional
Aprendizaje por Refuerzo
Embeddings de grafos
GRL no supervisado
Embedding de grafo entero
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/166757

id SEDICI_a6df07481aa332b4d378761080a49bbb
oai_identifier_str oai:sedici.unlp.edu.ar:10915/166757
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Graph representations for reinforcement learningRepresentaciones de grafos para aprendizaje por refuerzoSchab, EstebanCasanova, CarlosPiccoli, FabianaCiencias InformáticasComputational IntelligenceReinforcement LearningGraph Embeddingsunsupervised GRLWhole Graph EmbeddingInteligencia ComputacionalAprendizaje por RefuerzoEmbeddings de grafosGRL no supervisadoEmbedding de grafo enteroGraph analysis is becoming increasingly important due to the expressive power of graph models and the efficient algorithms available for processing them. Reinforcement Learning is one domain that could benefit from advancements in graph analysis, given that a learning agent may be integrated into an environment that can be represented as a graph. Nevertheless, the structural irregularity of graphs and the lack of prior labels make it difficult to integrate such a model into modern Reinforcement Learning frameworks that rely on artificial neural networks. Graph embedding enables the learning of low-dimensional vector representations that are more suited for machine learning algorithms, while retaining essential graph features. This paper presents a framework for evaluating graph embedding algorithms and their ability to preserve the structure and relevant features of graphs by means of an internal validation metric, without resorting to subsequent tasks that require labels for training. Based on this framework, three defined algorithms that meet the necessary requirements for solving a specific problem of Reinforcement Learning in graphs are selected, analyzed, and compared. These algorithms are Graph2Vec, GL2Vec, and Wavelet Characteristics, with the latter two demonstrating superior performance.El análisis de grafos es un tópico emergente debido a la expresividad de los modelos basados en grafos y al desarrollo de algoritmos para su procesamiento. Un área que puede beneficiarse de estos avances es el aprendizaje por refuerzo, dado que un agente de aprendizaje puede estar imnerso en un entorno modelable como un grafo. Sin embargo, tanto la irregularidad de las características estructurales de los grafos como la ausencia de etiquetas a priori dificultan la incorporación de un modelo de este tipo en los marcos modernos de Aprendizaje por Refuerzo basados en redes neuronales artificiales. En este sentido, los embeddings de grafos permiten aprender representaciones vectoriales de baja dimensión, más adecuadas para los algoritmos de aprendizaje automático, preservando al mismo tiempo las características clave de los grafos. Proponemos un marco para evaluar algoritmos de Graph Embedding y su capacidad para preservar la estructura y características relevantes de los grafos mediante una métrica de validación interna, sin recurrir a tareas posteriores que requieran etiquetas para el entrenamiento. Aplicando este marco con un problema concreto, se seleccionan, analizan y comparan tres algoritmos que cumplen los requisitos necesarios: Graph2Vec, GL2Vec y Wavelet Characteristics, donde los dos últimos muestran un mejor comportamiento.Facultad de Informática2024-04info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionArticulohttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdf29-38http://sedici.unlp.edu.ar/handle/10915/166757enginfo:eu-repo/semantics/altIdentifier/issn/1666-6038info:eu-repo/semantics/altIdentifier/doi/10.24215/16666038.24.e03info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-10-15T11:36:11Zoai:sedici.unlp.edu.ar:10915/166757Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-10-15 11:36:11.752SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Graph representations for reinforcement learning
Representaciones de grafos para aprendizaje por refuerzo
title Graph representations for reinforcement learning
spellingShingle Graph representations for reinforcement learning
Schab, Esteban
Ciencias Informáticas
Computational Intelligence
Reinforcement Learning
Graph Embeddings
unsupervised GRL
Whole Graph Embedding
Inteligencia Computacional
Aprendizaje por Refuerzo
Embeddings de grafos
GRL no supervisado
Embedding de grafo entero
title_short Graph representations for reinforcement learning
title_full Graph representations for reinforcement learning
title_fullStr Graph representations for reinforcement learning
title_full_unstemmed Graph representations for reinforcement learning
title_sort Graph representations for reinforcement learning
dc.creator.none.fl_str_mv Schab, Esteban
Casanova, Carlos
Piccoli, Fabiana
author Schab, Esteban
author_facet Schab, Esteban
Casanova, Carlos
Piccoli, Fabiana
author_role author
author2 Casanova, Carlos
Piccoli, Fabiana
author2_role author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
Computational Intelligence
Reinforcement Learning
Graph Embeddings
unsupervised GRL
Whole Graph Embedding
Inteligencia Computacional
Aprendizaje por Refuerzo
Embeddings de grafos
GRL no supervisado
Embedding de grafo entero
topic Ciencias Informáticas
Computational Intelligence
Reinforcement Learning
Graph Embeddings
unsupervised GRL
Whole Graph Embedding
Inteligencia Computacional
Aprendizaje por Refuerzo
Embeddings de grafos
GRL no supervisado
Embedding de grafo entero
dc.description.none.fl_txt_mv Graph analysis is becoming increasingly important due to the expressive power of graph models and the efficient algorithms available for processing them. Reinforcement Learning is one domain that could benefit from advancements in graph analysis, given that a learning agent may be integrated into an environment that can be represented as a graph. Nevertheless, the structural irregularity of graphs and the lack of prior labels make it difficult to integrate such a model into modern Reinforcement Learning frameworks that rely on artificial neural networks. Graph embedding enables the learning of low-dimensional vector representations that are more suited for machine learning algorithms, while retaining essential graph features. This paper presents a framework for evaluating graph embedding algorithms and their ability to preserve the structure and relevant features of graphs by means of an internal validation metric, without resorting to subsequent tasks that require labels for training. Based on this framework, three defined algorithms that meet the necessary requirements for solving a specific problem of Reinforcement Learning in graphs are selected, analyzed, and compared. These algorithms are Graph2Vec, GL2Vec, and Wavelet Characteristics, with the latter two demonstrating superior performance.
El análisis de grafos es un tópico emergente debido a la expresividad de los modelos basados en grafos y al desarrollo de algoritmos para su procesamiento. Un área que puede beneficiarse de estos avances es el aprendizaje por refuerzo, dado que un agente de aprendizaje puede estar imnerso en un entorno modelable como un grafo. Sin embargo, tanto la irregularidad de las características estructurales de los grafos como la ausencia de etiquetas a priori dificultan la incorporación de un modelo de este tipo en los marcos modernos de Aprendizaje por Refuerzo basados en redes neuronales artificiales. En este sentido, los embeddings de grafos permiten aprender representaciones vectoriales de baja dimensión, más adecuadas para los algoritmos de aprendizaje automático, preservando al mismo tiempo las características clave de los grafos. Proponemos un marco para evaluar algoritmos de Graph Embedding y su capacidad para preservar la estructura y características relevantes de los grafos mediante una métrica de validación interna, sin recurrir a tareas posteriores que requieran etiquetas para el entrenamiento. Aplicando este marco con un problema concreto, se seleccionan, analizan y comparan tres algoritmos que cumplen los requisitos necesarios: Graph2Vec, GL2Vec y Wavelet Characteristics, donde los dos últimos muestran un mejor comportamiento.
Facultad de Informática
description Graph analysis is becoming increasingly important due to the expressive power of graph models and the efficient algorithms available for processing them. Reinforcement Learning is one domain that could benefit from advancements in graph analysis, given that a learning agent may be integrated into an environment that can be represented as a graph. Nevertheless, the structural irregularity of graphs and the lack of prior labels make it difficult to integrate such a model into modern Reinforcement Learning frameworks that rely on artificial neural networks. Graph embedding enables the learning of low-dimensional vector representations that are more suited for machine learning algorithms, while retaining essential graph features. This paper presents a framework for evaluating graph embedding algorithms and their ability to preserve the structure and relevant features of graphs by means of an internal validation metric, without resorting to subsequent tasks that require labels for training. Based on this framework, three defined algorithms that meet the necessary requirements for solving a specific problem of Reinforcement Learning in graphs are selected, analyzed, and compared. These algorithms are Graph2Vec, GL2Vec, and Wavelet Characteristics, with the latter two demonstrating superior performance.
publishDate 2024
dc.date.none.fl_str_mv 2024-04
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Articulo
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://sedici.unlp.edu.ar/handle/10915/166757
url http://sedici.unlp.edu.ar/handle/10915/166757
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/issn/1666-6038
info:eu-repo/semantics/altIdentifier/doi/10.24215/16666038.24.e03
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
29-38
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1846064385231945728
score 13.22299